Landing page v0.2.0 updates: multi-engine copy, star count, model cards, voice creator section, responsive ControlUI, iOS audio fix

- Replace Qwen-specific copy with multi-engine messaging across hero, meta, and features
- Add GitHub star count fetched server-side via /api/stars with Spacedrive-style navbar badge
- Replace 'Why Voicebox exists' section with model cards for all 4 TTS engines
- Enable Linux download card (was 'Coming soon')
- Update GPU support copy to include ROCm, Intel Arc, DirectML
- Add Voice Creator section with animated 3-tab UI (upload, mic, system audio) and waveform background
- Make ControlUI responsive: horizontal scroll cards on mobile, stacked layout, scroll-to-active profile
- Fix iOS Safari audio autoplay (unlock AudioContext on user gesture)
- Fix hero logo square background with mix-blend-lighten
- Remove generation length green coloring, use gray with accent highlights
- Comment out grain overlay (visible tile seams)
- Remove player close button, stack waveform above controls on mobile
- Fixed-height profile cards (143px) with space between badges and buttons
This commit is contained in:
James Pine
2026-03-15 04:53:28 -07:00
parent 8377152d86
commit f80782a90a
16 changed files with 1756 additions and 462 deletions
+31 -133
View File
@@ -139,7 +139,11 @@ export function AudioPlayer() {
barRadius: 2,
height: 80,
normalize: true,
backend: 'WebAudio',
// Use MediaElement backend (default). Unlike the WebAudio backend,
// MediaElement uses a standard <audio> element for playback which
// benefits from the browser/webview's built-in audio session recovery.
// This prevents audio loss when another app steals audio output or
// the system audio session is interrupted.
interact: true, // Enable interaction (click to seek)
mediaControls: false, // Don't show native controls
});
@@ -189,15 +193,6 @@ export function AudioPlayer() {
const currentVolume = usePlayerStore.getState().volume;
wavesurfer.setVolume(currentVolume);
// Get the underlying audio element and ensure it's not muted
// (unless we're using native playback, which will be set later)
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement && !isUsingNativePlaybackRef.current) {
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log('Audio element volume:', mediaElement.volume, 'muted:', mediaElement.muted);
}
// Auto-play when ready - check if we should use native playback
// Get current values from the store and queries at runtime (not captured closure values)
const currentAudioUrl = usePlayerStore.getState().audioUrl;
@@ -264,21 +259,8 @@ export function AudioPlayer() {
debug.log('Should use native playback:', shouldUseNative);
if (!shouldUseNative) {
debug.log('No custom devices assigned, falling back to WaveSurfer');
// Reset native playback flag and unmute WaveSurfer
debug.log('No custom devices assigned, using standard playback');
isUsingNativePlaybackRef.current = false;
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
const currentVolume = usePlayerStore.getState().volume;
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log(
'WaveSurfer unmuted for normal playback - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
} else {
const deviceIds = assignedChannels.flatMap((ch: any) => ch.device_ids);
debug.log('Device IDs to play to:', deviceIds);
@@ -299,19 +281,10 @@ export function AudioPlayer() {
// Mark that we're using native playback
isUsingNativePlaybackRef.current = true;
// Mute WaveSurfer's audio element to prevent UI audio output
// Keep WaveSurfer running for visualization
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
mediaElement.volume = 0;
mediaElement.muted = true;
debug.log(
'WaveSurfer muted for native playback - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
// Mute WaveSurfer's audio output — native handles the actual sound
// Keep WaveSurfer running for waveform visualization
wavesurfer.setVolume(0);
wavesurfer.setMuted(true);
// Start WaveSurfer playback for visualization (muted)
wavesurfer.play().catch((error) => {
@@ -334,38 +307,15 @@ export function AudioPlayer() {
'Native playback failed during auto-play, falling back to WaveSurfer:',
error,
);
// Reset native playback flag and unmute WaveSurfer
isUsingNativePlaybackRef.current = false;
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
const currentVolume = usePlayerStore.getState().volume;
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log(
'WaveSurfer unmuted after native playback failure - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
// Fall through to WaveSurfer playback
}
} else {
debug.log('Not using native playback, using WaveSurfer');
// Reset native playback flag and unmute WaveSurfer
isUsingNativePlaybackRef.current = false;
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
const currentVolume = usePlayerStore.getState().volume;
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log(
'WaveSurfer unmuted for normal playback - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
}
// Standard playback path — ensure WaveSurfer is unmuted
if (!isUsingNativePlaybackRef.current) {
wavesurfer.setMuted(false);
wavesurfer.setVolume(usePlayerStore.getState().volume);
}
// Only auto-play if shouldAutoPlay flag is set (user explicitly clicked to play)
@@ -389,28 +339,6 @@ export function AudioPlayer() {
// Handle play/pause
wavesurfer.on('play', () => {
setIsPlaying(true);
// Ensure audio element volume is set correctly
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
// Double-check: if using native playback, keep WaveSurfer muted
// Otherwise, ensure it's unmuted
if (isUsingNativePlaybackRef.current) {
mediaElement.volume = 0;
mediaElement.muted = true;
debug.log('Playing (native mode) - WaveSurfer muted for visualization only');
} else {
// Ensure WaveSurfer is unmuted for normal playback
const currentVolume = usePlayerStore.getState().volume;
mediaElement.volume = currentVolume;
mediaElement.muted = false;
debug.log(
'Playing (normal mode) - volume:',
mediaElement.volume,
'muted:',
mediaElement.muted,
);
}
}
});
wavesurfer.on('pause', () => setIsPlaying(false));
wavesurfer.on('finish', () => {
@@ -492,11 +420,6 @@ export function AudioPlayer() {
if (wavesurferRef.current) {
debug.log('Destroying WaveSurfer instance');
try {
const mediaElement = wavesurferRef.current.getMediaElement();
if (mediaElement) {
mediaElement.pause();
mediaElement.src = '';
}
wavesurferRef.current.destroy();
} catch (error) {
debug.error('Error destroying WaveSurfer:', error);
@@ -537,13 +460,10 @@ export function AudioPlayer() {
}
// Reset native playback flag when loading new audio
// Also unmute WaveSurfer if it was muted
// Unmute WaveSurfer if it was muted for native playback
if (isUsingNativePlaybackRef.current) {
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
mediaElement.muted = false;
mediaElement.volume = usePlayerStore.getState().volume;
}
wavesurfer.setMuted(false);
wavesurfer.setVolume(usePlayerStore.getState().volume);
}
isUsingNativePlaybackRef.current = false;
@@ -559,16 +479,7 @@ export function AudioPlayer() {
wavesurfer.pause();
}
// Stop the media element explicitly
const mediaElement = wavesurfer.getMediaElement();
if (mediaElement) {
debug.log('Stopping media element');
mediaElement.pause();
mediaElement.currentTime = 0;
mediaElement.src = '';
}
// Use empty() to completely destroy the waveform and media element
// Use empty() to completely destroy the waveform and reset media
debug.log('Calling wavesurfer.empty() to destroy audio');
wavesurfer.empty();
} catch (error) {
@@ -623,20 +534,13 @@ export function AudioPlayer() {
// Sync volume
useEffect(() => {
if (wavesurferRef.current) {
wavesurferRef.current.setVolume(volume);
// Also ensure the underlying audio element volume is set
const mediaElement = wavesurferRef.current.getMediaElement();
if (mediaElement) {
// If using native playback, keep WaveSurfer muted regardless of volume setting
if (isUsingNativePlaybackRef.current) {
mediaElement.volume = 0;
mediaElement.muted = true;
debug.log('Volume sync: Using native playback, keeping WaveSurfer muted');
} else {
mediaElement.volume = volume;
mediaElement.muted = volume === 0;
debug.log('Volume synced:', volume, 'muted:', mediaElement.muted);
}
// If using native playback, keep WaveSurfer muted regardless of volume setting
if (isUsingNativePlaybackRef.current) {
wavesurferRef.current.setVolume(0);
debug.log('Volume sync: Using native playback, keeping WaveSurfer muted');
} else {
wavesurferRef.current.setVolume(volume);
debug.log('Volume synced:', volume);
}
}
}, [volume]);
@@ -757,11 +661,8 @@ export function AudioPlayer() {
isUsingNativePlaybackRef.current = true;
// Mute WaveSurfer and start it for visualization
const mediaElement = wavesurferRef.current.getMediaElement();
if (mediaElement) {
mediaElement.volume = 0;
mediaElement.muted = true;
}
wavesurferRef.current.setVolume(0);
wavesurferRef.current.setMuted(true);
// Start WaveSurfer for visualization (muted)
wavesurferRef.current.play().catch((error) => {
@@ -785,11 +686,8 @@ export function AudioPlayer() {
} else {
// Ensure WaveSurfer is not muted if not using native playback
if (!isUsingNativePlaybackRef.current) {
const mediaElement = wavesurferRef.current.getMediaElement();
if (mediaElement) {
mediaElement.muted = false;
mediaElement.volume = volume;
}
wavesurferRef.current.setMuted(false);
wavesurferRef.current.setVolume(volume);
}
wavesurferRef.current.play().catch((error) => {
@@ -5,6 +5,14 @@ import { useEffect, useRef, useState } from 'react';
import { EffectsChainEditor } from '@/components/Effects/EffectsChainEditor';
import { GenerationPicker } from '@/components/Effects/GenerationPicker';
import { Button } from '@/components/ui/button';
import {
Dialog,
DialogContent,
DialogDescription,
DialogFooter,
DialogHeader,
DialogTitle,
} from '@/components/ui/dialog';
import { Input } from '@/components/ui/input';
import { Label } from '@/components/ui/label';
import { Separator } from '@/components/ui/separator';
@@ -29,6 +37,11 @@ export function EffectsDetail() {
const [saving, setSaving] = useState(false);
const [deleting, setDeleting] = useState(false);
// "Save as Custom" dialog state
const [saveAsDialogOpen, setSaveAsDialogOpen] = useState(false);
const [saveAsName, setSaveAsName] = useState('');
const [saveAsDescription, setSaveAsDescription] = useState('');
// Preview state
const [previewGenId, setPreviewGenId] = useState<string | null>(null);
const [previewLoading, setPreviewLoading] = useState(false);
@@ -165,8 +178,38 @@ export function EffectsDetail() {
}
}
async function handleSaveAsNew() {
await handleSaveNew();
function handleSaveAsNew() {
// Open the dialog with a suggested name based on the current preset
setSaveAsName(`${name} (Copy)`);
setSaveAsDescription(description);
setSaveAsDialogOpen(true);
}
async function handleSaveAsConfirm() {
if (!saveAsName.trim()) {
toast({ title: 'Name required', variant: 'destructive' });
return;
}
setSaving(true);
try {
const created = await apiClient.createEffectPreset({
name: saveAsName.trim(),
description: saveAsDescription.trim() || undefined,
effects_chain: workingChain,
});
queryClient.invalidateQueries({ queryKey: ['effect-presets'] });
setSaveAsDialogOpen(false);
setSelectedPresetId(created.id);
toast({ title: 'Preset saved', description: `"${created.name}" has been created.` });
} catch (error) {
toast({
title: 'Failed to save',
description: error instanceof Error ? error.message : 'Unknown error',
variant: 'destructive',
});
} finally {
setSaving(false);
}
}
async function handleDelete() {
@@ -327,6 +370,53 @@ export function EffectsDetail() {
</p>
</div>
</div>
{/* Save as Custom dialog */}
<Dialog open={saveAsDialogOpen} onOpenChange={setSaveAsDialogOpen}>
<DialogContent className="sm:max-w-md">
<DialogHeader>
<DialogTitle>Save as Custom Preset</DialogTitle>
<DialogDescription>
Create a new custom preset based on the current effects chain.
</DialogDescription>
</DialogHeader>
<div className="space-y-3 py-2">
<div className="space-y-1.5">
<Label className="text-xs">Name</Label>
<Input
value={saveAsName}
onChange={(e) => setSaveAsName(e.target.value)}
placeholder="My preset..."
className="h-9"
autoFocus
onKeyDown={(e) => {
if (e.key === 'Enter' && saveAsName.trim()) {
handleSaveAsConfirm();
}
}}
/>
</div>
<div className="space-y-1.5">
<Label className="text-xs">Description</Label>
<Textarea
value={saveAsDescription}
onChange={(e) => setSaveAsDescription(e.target.value)}
placeholder="Describe what this preset does..."
className="min-h-[60px] resize-none"
/>
</div>
</div>
<DialogFooter>
<Button variant="outline" onClick={() => setSaveAsDialogOpen(false)} disabled={saving}>
Cancel
</Button>
<Button onClick={handleSaveAsConfirm} disabled={saving || !saveAsName.trim()}>
<Save className="h-3.5 w-3.5 mr-1.5" />
{saving ? 'Saving...' : 'Save'}
</Button>
</DialogFooter>
</DialogContent>
</Dialog>
</div>
);
}
+5 -2
View File
@@ -45,12 +45,15 @@ export function Sidebar({ isMacOS }: SidebarProps) {
{/* Navigation Buttons */}
<div className="flex flex-col gap-3">
{tabs.map((tab) => {
{tabs.map((tab, index) => {
const Icon = tab.icon;
// For index route, use exact match; for others, use default matching
const isActive =
tab.path === '/' ? matchRoute({ to: '/', exact: true }) : matchRoute({ to: tab.path });
// Accent fades as buttons get further from the logo
const accentOpacity = Math.max(0.08, 0.5 - index * 0.07);
return (
<Link
key={tab.id}
@@ -70,7 +73,7 @@ export function Sidebar({ isMacOS }: SidebarProps) {
style={{
maskImage: 'linear-gradient(to bottom, black, transparent 60%)',
WebkitMaskImage: 'linear-gradient(to bottom, black, transparent 60%)',
border: '1px solid hsl(var(--accent) / 0.5)',
border: `1px solid hsl(var(--accent) / ${accentOpacity})`,
}}
/>
)}
+163
View File
@@ -0,0 +1,163 @@
# Voicebox v0.2.0 -- Release Notes
## The story
Voicebox v0.1.x shipped as a single-engine voice cloning app built around Qwen3-TTS. It worked, but it was limited: one model family, 10 languages, English-centric emotion, a synchronous generation pipeline that locked the UI, and a hard ceiling on how much text you could generate at once.
v0.2.0 is a ground-up rethink. Voicebox is now a **multi-engine voice cloning platform**. Four TTS engines. 23 languages. Expressive paralinguistic controls. A full post-processing effects pipeline. Unlimited generation length. Asynchronous everything. And it runs on every major GPU vendor -- NVIDIA, AMD, Intel Arc, Apple Silicon -- plus Docker for headless deployment.
This is the release where Voicebox stops being a proof of concept and starts being a real tool.
---
## Major New Features
### Multi-Engine Architecture
Voicebox now supports **four TTS engines**, each with different strengths. Switch between them per-generation from a single unified interface:
| Engine | Languages | Strengths |
|--------|-----------|-----------|
| **Qwen3-TTS** (0.6B / 1.7B) | 10 | High-quality multilingual cloning, delivery instructions ("speak slowly", "whisper") |
| **LuxTTS** | English | Lightweight (~1GB VRAM), 48kHz output, 150x realtime on CPU |
| **Chatterbox Multilingual** | 23 | Broadest language coverage -- Arabic, Danish, Finnish, Greek, Hebrew, Hindi, Malay, Norwegian, Polish, Swahili, Swedish, Turkish and more |
| **Chatterbox Turbo** | English | Fast 350M model with paralinguistic emotion/sound tags |
### Emotions and Paralinguistic Tags (Chatterbox Turbo)
Type `/` in the text input to open an autocomplete for **9 expressive tags** that the model synthesizes inline with speech:
`[laugh]` `[chuckle]` `[gasp]` `[cough]` `[sigh]` `[groan]` `[sniff]` `[shush]` `[clear throat]`
Tags render as inline badges in a rich text editor and serialize cleanly to the API. This makes generated speech sound natural and expressive in a way that plain TTS can't.
### 23 Languages via Chatterbox Multilingual
The Chatterbox Multilingual engine brings zero-shot voice cloning to **23 languages**: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. The language dropdown dynamically filters to show only languages supported by the selected engine.
### Unlimited Generation Length (Auto-Chunking)
Previously, long text would hit model context limits and degrade. Now, text is **automatically split at sentence boundaries** and each chunk is generated independently, then crossfaded back together. This is fully engine-agnostic and works with all four engines.
- **Auto-chunking limit slider** (100-5,000 chars, default 800) -- controls when text gets split
- **Crossfade slider** (0-200ms, default 50ms) -- blends chunk boundaries smoothly, or set to 0 for a hard cut
- **Max text length raised to 50,000 characters** -- generate entire scripts, chapters, or articles in one go
- Smart splitting respects abbreviations (Dr., e.g., a.m.), CJK punctuation, and never breaks inside paralinguistic `[tags]`
### Asynchronous Generation Queue
Generation is now fully **non-blocking**. Submit a generation and immediately start typing the next one -- no more frozen UI waiting for inference to complete.
- Serial execution queue prevents GPU contention across all backends
- Real-time SSE status streaming (`generating` -> `completed` / `failed`)
- Failed generations can be retried without re-entering text
- Stale generations from crashes are auto-recovered on startup
- Generating status pill shown inline in the story editor
### Post-Processing Effects Pipeline
A full audio effects system powered by Spotify's `pedalboard` library. Apply effects after generation, preview them in real time, and build reusable presets -- all without leaving the app.
**8 effects available:**
| Effect | What it does |
|--------|-------------|
| **Pitch Shift** | Shift pitch up or down by up to 12 semitones |
| **Reverb** | Room reverb with configurable size, damping, and wet/dry mix |
| **Delay** | Echo with adjustable delay time, feedback, and mix |
| **Chorus / Flanger** | Modulated delay -- short for metallic flanger, longer for lush chorus |
| **Compressor** | Dynamic range compression with threshold, ratio, attack, and release |
| **Gain** | Volume adjustment from -40 to +40 dB |
| **High-Pass Filter** | Remove low frequencies below a configurable cutoff |
| **Low-Pass Filter** | Remove high frequencies above a configurable cutoff |
**Effects presets** -- Four built-in presets ship out of the box (Robotic, Radio, Echo Chamber, Deep Voice), and you can create unlimited custom presets. Presets are drag-and-drop chains of effects with per-parameter sliders.
**Per-profile default effects** -- Assign an effects chain to a voice profile and it applies automatically to every generation with that voice. Override per-generation from the generate box.
**Live preview** -- Audition any effects chain against an existing generation before committing. The preview streams processed audio without saving anything.
### Generation Versions
Every generation now supports **multiple versions** with full provenance tracking:
- **Original** -- the clean, unprocessed TTS output (always preserved)
- **Effects versions** -- apply different effects chains to create new versions from any source version
- **Takes** -- regenerate with the same text and voice but a new seed for variation
- **Source tracking** -- each version records which version it was derived from
- **Version pinning in stories** -- pin a specific version to a track clip in the story editor, independent of the generation's default
- **Favorites** -- star generations to mark them for quick access
---
## New Platform Support
### Linux (Native)
Full Linux support with `.deb` and `.rpm` packages. Includes PulseAudio/PipeWire audio capture for voice sample recording.
### AMD ROCm GPU Acceleration
AMD GPU users now get hardware-accelerated inference via ROCm, with automatic `HSA_OVERRIDE_GFX_VERSION` configuration for GPUs not officially in the ROCm compatibility list (e.g., RX 6600).
### NVIDIA CUDA Backend Swap
The CPU-only release can download and swap in a CUDA-accelerated backend binary from within the app -- no reinstall required. Handles GitHub's 2GB asset limit by downloading split parts and verifying SHA-256 checksums.
### Intel Arc (XPU) and DirectML
PyTorch backend also supports Intel Arc GPUs via IPEX/XPU and Windows any-GPU via DirectML.
### Docker + Web Deployment
Run Voicebox headless as a Docker container with the full web UI:
```bash
docker compose up
```
3-stage build, non-root runtime, health checks, persistent model cache across rebuilds. Binds to localhost only by default.
---
## Model Management
- **Per-model unload** -- free GPU memory without deleting downloaded models
- **Custom models directory** -- set `VOICEBOX_MODELS_DIR` to store models anywhere
- **Model folder migration** -- move all models to a new location with progress tracking
- **Whisper Turbo** -- added `openai/whisper-large-v3-turbo` as a transcription model option
- **Download cancel/clear UI** -- cancel in-progress downloads, VS Code-style problems panel for errors
---
## Security
- **CORS hardening** -- replaced wildcard `*` with an explicit allowlist of local origins; extensible via `VOICEBOX_CORS_ORIGINS` env var
- **Network access toggle** -- fully disable outbound network requests for air-gapped deployments
## Accessibility
- Comprehensive screen reader support (tested with NVDA/Narrator) across all major UI surfaces
- Keyboard navigation for voice cards, history rows, model management, and story editor
- State-aware `aria-label` attributes on all interactive controls
## Reliability
- **Atomic audio saves** -- two-phase write prevents corrupted files on crash/interrupt
- **Filesystem health endpoint** -- proactive disk space and directory writability checks
- **Errno-specific error messages** -- clear feedback for permission denied, disk full, missing directory
## UX Polish
- Responsive layout with horizontal-scroll voice cards on mobile
- App version shown in sidebar
- Voice card heights normalized
- Audio player title hidden at narrow widths to prevent overflow
---
## Installation
| Platform | Download |
|----------|----------|
| **macOS (Apple Silicon)** | `Voicebox_0.2.0_aarch64.dmg` |
| **macOS (Intel)** | `Voicebox_0.2.0_x64.dmg` |
| **Windows** | `Voicebox_0.2.0_x64_en-US.msi` or `x64-setup.exe` |
| **Linux** | `.deb` / `.rpm` packages |
| **Docker** | `docker compose up` |
The app includes automatic updates -- future patches will be installed automatically.
---
## Video Script Beats
For the marketing video, focus on these six beats:
1. **"Four engines, one app"** -- show the engine dropdown switching between Qwen, LuxTTS, Chatterbox, and Turbo
2. **"23 languages"** -- generate the same voice clone in Arabic, Japanese, Hindi, etc.
3. **"Make it expressive"** -- type `/laugh` and `/sigh` with Chatterbox Turbo, play back the result
4. **"Shape your sound"** -- apply the Robotic or Deep Voice preset, preview it live, then build a custom effects chain with drag-and-drop
5. **"No limits"** -- paste a long script, show it auto-chunk and generate seamlessly
6. **"Queue and go"** -- fire off multiple generations back-to-back without waiting
+15
View File
@@ -0,0 +1,15 @@
import { NextResponse } from 'next/server';
import { getStarCount } from '@/lib/releases';
export const dynamic = 'force-dynamic';
export const revalidate = 600;
export async function GET() {
try {
const count = await getStarCount();
return NextResponse.json({ count });
} catch (error) {
console.error('Error fetching star count:', error);
return NextResponse.json({ error: 'Failed to fetch star count' }, { status: 500 });
}
}
+5 -4
View File
@@ -116,16 +116,17 @@
}
/* Noise texture overlay for hero glow */
.hero-glow::after {
/* .hero-glow::after {
content: "";
position: absolute;
inset: 0;
z-index: 5;
pointer-events: none;
background-image: url("data:image/svg+xml,%3Csvg viewBox='0 0 512 512' xmlns='http://www.w3.org/2000/svg'%3E%3Cfilter id='noiseFilter'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='1.8' numOctaves='5' stitchTiles='stitch'/%3E%3C/filter%3E%3Crect width='100%25' height='100%25' filter='url(%23noiseFilter)'/%3E%3C/svg%3E");
opacity: 0.3;
background: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' width='2048' height='2048'%3E%3Cfilter id='n'%3E%3CfeTurbulence type='fractalNoise' baseFrequency='1.5' numOctaves='4' stitchTiles='stitch'/%3E%3C/filter%3E%3Crect width='100%25' height='100%25' filter='url(%23n)'/%3E%3C/svg%3E") center / 100% 100% no-repeat;
opacity: 0.35;
mix-blend-mode: overlay;
}
will-change: transform;
} */
/* Scrollbar hiding */
::-webkit-scrollbar {
+10 -2
View File
@@ -4,11 +4,11 @@ import './globals.css';
export const metadata: Metadata = {
title: 'Voicebox - Open Source Voice Cloning Desktop App',
description:
'Near-perfect voice cloning powered by Qwen3-TTS. Desktop app for Mac, Windows, and Linux. Multi-sample support, smart caching, local or remote inference.',
'Near-perfect voice cloning with multiple TTS engines. Desktop app for Mac, Windows, and Linux. Multi-sample support, smart caching, local or remote inference.',
keywords: [
'voice cloning',
'TTS',
'Qwen3',
'multi-engine',
'desktop app',
'AI voice',
'open source',
@@ -32,6 +32,14 @@ export const metadata: Metadata = {
export default function RootLayout({ children }: { children: React.ReactNode }) {
return (
<html lang="en" suppressHydrationWarning className="dark">
<head>
<link rel="preconnect" href="https://fonts.googleapis.com" />
<link rel="preconnect" href="https://fonts.gstatic.com" crossOrigin="anonymous" />
<link
href="https://fonts.googleapis.com/css2?family=Caveat:wght@400;500&display=swap"
rel="stylesheet"
/>
</head>
<body>
<div className="relative min-h-screen bg-background font-sans">{children}</div>
</body>
+133 -33
View File
@@ -1,6 +1,6 @@
'use client';
import { Github } from 'lucide-react';
import { Github, Globe, Languages, MessageSquare, Zap } from 'lucide-react';
import Image from 'next/image';
import { useEffect, useState } from 'react';
import { ControlUI } from '@/components/ControlUI';
@@ -8,6 +8,7 @@ import { Features } from '@/components/Features';
import { Footer } from '@/components/Footer';
import { Navbar } from '@/components/Navbar';
import { AppleIcon, LinuxIcon, WindowsIcon } from '@/components/PlatformIcons';
import { VoiceCreator } from '@/components/VoiceCreator';
import { DOWNLOAD_LINKS, GITHUB_REPO } from '@/lib/constants';
import type { DownloadLinks } from '@/lib/releases';
@@ -44,18 +45,18 @@ export default function Home() {
{/* Logo */}
<div
className="fade-in mx-auto mb-8 h-[120px] w-[120px] md:h-[160px] md:w-[160px]"
style={{ animationDelay: '0ms' }}
style={{
animationDelay: '0ms',
filter:
'drop-shadow(0 0 20px hsl(43 60% 50% / 0.4)) drop-shadow(0 0 60px hsl(43 60% 50% / 0.2))',
}}
>
<Image
src="/voicebox-logo-app.webp"
alt="Voicebox"
width={160}
height={160}
className="h-full w-full object-contain"
style={{
filter:
'drop-shadow(0 0 20px hsl(43 60% 50% / 0.4)) drop-shadow(0 0 60px hsl(43 60% 50% / 0.2))',
}}
className="h-full w-full object-contain mix-blend-lighten"
priority
/>
</div>
@@ -72,8 +73,8 @@ export default function Home() {
className="fade-in mx-auto mt-6 max-w-2xl text-lg text-muted-foreground md:text-xl"
style={{ animationDelay: '200ms' }}
>
Open source voice cloning studio powered by Qwen3-TTS. Clone any voice, generate natural
speech, and compose multi-voice projects all running locally.
Open source voice cloning studio with support for multiple TTS engines. Clone any voice,
generate natural speech, and compose multi-voice projects all running locally.
</p>
{/* CTAs */}
@@ -116,27 +117,125 @@ export default function Home() {
{/* ── Features ─────────────────────────────────────────────── */}
<Features />
{/* ── About / Manifesto ────────────────────────────────────── */}
{/* ── Voice Creator ────────────────────────────────────────── */}
<VoiceCreator />
{/* ── Models ─────────────────────────────────────────────────── */}
<section id="about" className="border-t border-border py-24">
<div className="mx-auto max-w-3xl px-6">
<h2 className="mb-10 text-center text-3xl font-semibold tracking-tight text-foreground md:text-4xl">
Why Voicebox exists
</h2>
<div className="space-y-6 text-center">
<p className="text-base leading-relaxed text-muted-foreground">
Cloud voice cloning services lock your voice data behind subscriptions, rate limits,
and terms of service that can change at any time. Your voice and the voices you
clone should belong to you.
</p>
<p className="text-lg font-medium text-foreground">
Voicebox is a local-first voice cloning studio. Download a model, clone any voice from
a few seconds of audio, and generate speech entirely on your machine.
</p>
<p className="text-sm leading-relaxed text-muted-foreground">
Optimized with Metal acceleration on Mac and CUDA on Windows/Linux. No Python install
required. No cloud. No subscriptions. Free and open-source, forever.
<div className="mx-auto max-w-5xl px-6">
<div className="text-center mb-14">
<h2 className="text-3xl font-semibold tracking-tight text-foreground md:text-4xl mb-4">
Multi-Engine Architecture
</h2>
<p className="text-muted-foreground max-w-2xl mx-auto">
Choose the right model for every job. All models run locally on your hardware
download once, use forever.
</p>
</div>
<div className="grid grid-cols-1 md:grid-cols-2 gap-4">
{/* Qwen3-TTS */}
<div className="rounded-xl border border-border bg-card/60 backdrop-blur-sm p-6 transition-colors hover:border-accent/30">
<div className="flex items-start justify-between mb-3">
<div>
<h3 className="text-base font-semibold text-foreground">Qwen3-TTS</h3>
<span className="text-xs text-muted-foreground/60">by Alibaba</span>
</div>
<div className="flex gap-1.5">
<span className="text-[10px] px-2 py-0.5 rounded-full border border-border bg-background text-muted-foreground">
1.7B
</span>
<span className="text-[10px] px-2 py-0.5 rounded-full border border-border bg-background text-muted-foreground">
0.6B
</span>
</div>
</div>
<p className="text-sm text-muted-foreground leading-relaxed mb-4">
High-quality multilingual voice cloning with natural prosody. The only engine with
delivery instructions control tone, pace, and emotion with natural language.
</p>
<div className="flex flex-wrap gap-2">
<span className="flex items-center gap-1 text-[11px] text-muted-foreground/70">
<Globe className="h-3 w-3" />
10 languages
</span>
<span className="flex items-center gap-1 text-[11px] text-muted-foreground/70">
<MessageSquare className="h-3 w-3" />
Delivery instructions
</span>
</div>
</div>
{/* Chatterbox */}
<div className="rounded-xl border border-border bg-card/60 backdrop-blur-sm p-6 transition-colors hover:border-accent/30">
<div className="flex items-start justify-between mb-3">
<div>
<h3 className="text-base font-semibold text-foreground">Chatterbox</h3>
<span className="text-xs text-muted-foreground/60">by Resemble AI</span>
</div>
</div>
<p className="text-sm text-muted-foreground leading-relaxed mb-4">
Production-grade voice cloning with the broadest language support. 23 languages with
zero-shot cloning and emotion exaggeration control.
</p>
<div className="flex flex-wrap gap-2">
<span className="flex items-center gap-1 text-[11px] text-muted-foreground/70">
<Languages className="h-3 w-3" />
23 languages
</span>
</div>
</div>
{/* Chatterbox Turbo */}
<div className="rounded-xl border border-border bg-card/60 backdrop-blur-sm p-6 transition-colors hover:border-accent/30">
<div className="flex items-start justify-between mb-3">
<div>
<h3 className="text-base font-semibold text-foreground">Chatterbox Turbo</h3>
<span className="text-xs text-muted-foreground/60">by Resemble AI</span>
</div>
<span className="text-[10px] px-2 py-0.5 rounded-full border border-border bg-background text-muted-foreground">
350M
</span>
</div>
<p className="text-sm text-muted-foreground leading-relaxed mb-4">
Lightweight and fast. Supports paralinguistic tags embed [laugh], [sigh], [gasp]
and more directly in your text for expressive, natural speech.
</p>
<div className="flex flex-wrap gap-2">
<span className="flex items-center gap-1 text-[11px] text-muted-foreground/70">
<Zap className="h-3 w-3" />
350M params
</span>
<span className="flex items-center gap-1 text-[11px] text-muted-foreground/70">
<MessageSquare className="h-3 w-3" />
[laugh] [sigh] tags
</span>
</div>
</div>
{/* LuxTTS */}
<div className="rounded-xl border border-border bg-card/60 backdrop-blur-sm p-6 transition-colors hover:border-accent/30">
<div className="flex items-start justify-between mb-3">
<div>
<h3 className="text-base font-semibold text-foreground">LuxTTS</h3>
<span className="text-xs text-muted-foreground/60">by ZipVoice</span>
</div>
</div>
<p className="text-sm text-muted-foreground leading-relaxed mb-4">
Ultra-fast, CPU-friendly voice cloning at 48kHz. Exceeds 150x realtime on CPU with
~1GB VRAM. The fastest engine for quick iterations.
</p>
<div className="flex flex-wrap gap-2">
<span className="flex items-center gap-1 text-[11px] text-muted-foreground/70">
<Zap className="h-3 w-3" />
150x realtime
</span>
<span className="flex items-center gap-1 text-[11px] text-muted-foreground/70">
48kHz output
</span>
</div>
</div>
</div>
</div>
</section>
@@ -193,16 +292,17 @@ export default function Home() {
</a>
{/* Linux */}
<div
className="flex items-center rounded-xl border border-border bg-card/60 backdrop-blur-sm px-5 py-4 opacity-50 cursor-not-allowed"
title="Linux builds coming soon"
<a
href={downloadLinks.linux}
download
className="flex items-center rounded-xl border border-border bg-card/60 backdrop-blur-sm px-5 py-4 transition-all hover:border-accent/30 hover:bg-card group"
>
<LinuxIcon className="h-6 w-6 shrink-0 text-muted-foreground" />
<LinuxIcon className="h-6 w-6 shrink-0 text-muted-foreground group-hover:text-foreground transition-colors" />
<div className="ml-4">
<div className="text-sm font-medium">Linux</div>
<div className="text-xs text-muted-foreground">Coming soon</div>
<div className="text-xs text-muted-foreground">AppImage (x64)</div>
</div>
</div>
</a>
</div>
{/* GitHub link */}
+194 -106
View File
@@ -17,7 +17,7 @@ import {
Wand2,
} from 'lucide-react';
import { useCallback, useEffect, useRef, useState } from 'react';
import { LandingAudioPlayer } from './LandingAudioPlayer';
import { LandingAudioPlayer, unlockAudioContext } from './LandingAudioPlayer';
// ─── Data ───────────────────────────────────────────────────────────────────
// Edit this section to customise all the content shown in the ControlUI demo.
@@ -29,7 +29,7 @@ interface VoiceProfile {
hasEffects: boolean;
}
/** Voice profiles shown in the 3×3 grid. Index matters — DemoScript references profiles by index. */
/** Voice profiles shown in the grid / scroll strip. Index matters — DemoScript references profiles by index. */
const PROFILES: VoiceProfile[] = [
{
name: 'Jarvis',
@@ -301,24 +301,27 @@ function LoadingBars({ mode }: { mode: 'idle' | 'generating' | 'playing' }) {
// ─── Profile Card ───────────────────────────────────────────────────────────
function ProfileCard({
const ProfileCard = ({
profile,
selected,
selecting,
cardRef,
}: {
profile: VoiceProfile;
selected: boolean;
selecting: boolean;
}) {
cardRef?: React.Ref<HTMLDivElement>;
}) => {
return (
<motion.div
className={`rounded-xl border-2 bg-card p-3.5 flex flex-col aspect-square transition-all duration-200 ${
ref={cardRef}
className={`rounded-xl border-2 bg-card p-3.5 flex flex-col h-[143px] transition-all duration-200 ${
selected ? 'border-accent shadow-md' : 'border-border/50 hover:shadow-sm'
} ${selecting && !selected ? 'opacity-60' : ''}`}
animate={selecting && selected ? { scale: [1, 1.02, 1] } : {}}
transition={{ duration: 0.3 }}
>
<div className="text-[15px] font-bold leading-tight">{profile.name}</div>
<div className="text-[15px] font-bold leading-tight line-clamp-2">{profile.name}</div>
<div className="text-[10px] text-muted-foreground line-clamp-2 leading-relaxed mt-1">
{profile.description}
</div>
@@ -335,7 +338,7 @@ function ProfileCard({
</div>
</motion.div>
);
}
};
// ─── History Row ────────────────────────────────────────────────────────────
@@ -416,79 +419,79 @@ function FloatingGenerateBox({
phase,
typingText,
selectedProfile,
engine,
effect,
}: {
phase: Phase;
typingText: string;
selectedProfile: VoiceProfile | null;
engine: string;
effect?: string;
}) {
const isFocused = phase === 'typing' || phase === 'generating';
const isGenerating = phase === 'generating';
return (
<div className="absolute left-3 right-3 z-20" style={{ bottom: 117 }}>
<motion.div
className="bg-background/30 backdrop-blur-2xl border border-accent/20 rounded-[1.5rem] shadow-2xl p-2.5"
animate={{
borderColor: isGenerating
? 'hsl(43 50% 45% / 0.35)'
: isFocused
? 'hsl(43 50% 45% / 0.25)'
: 'hsl(43 50% 45% / 0.15)',
}}
transition={{ duration: 0.3 }}
>
{/* Text area + generate button */}
<div className="flex items-start gap-2">
<div className="flex-1 min-w-0">
<motion.div
className="overflow-hidden"
animate={{ height: isFocused ? 100 : 32 }}
transition={{ duration: 0.25, ease: 'easeOut' }}
<motion.div
className="bg-background/30 backdrop-blur-2xl border border-accent/20 rounded-[1.5rem] shadow-2xl p-2.5"
animate={{
borderColor: isGenerating
? 'hsl(43 50% 45% / 0.35)'
: isFocused
? 'hsl(43 50% 45% / 0.25)'
: 'hsl(43 50% 45% / 0.15)',
}}
transition={{ duration: 0.3 }}
>
{/* Text area + generate button */}
<div className="flex items-start gap-2">
<div className="flex-1 min-w-0">
<motion.div
className="overflow-hidden"
animate={{ height: isFocused ? 100 : 32 }}
transition={{ duration: 0.25, ease: 'easeOut' }}
>
<div
className="text-[12.5px] text-muted-foreground/60 px-2 py-1 leading-relaxed"
style={{ minHeight: isFocused ? 100 : 32 }}
>
<div
className="text-[12.5px] text-muted-foreground/60 px-2 py-1 leading-relaxed"
style={{ minHeight: isFocused ? 100 : 32 }}
>
{phase === 'typing' ? (
<span className="text-foreground">
<TypewriterText text={typingText} />
</span>
) : phase === 'generating' ? (
<span className="text-muted-foreground/40">{typingText}</span>
) : (
<span>
{selectedProfile
? `Generate speech using ${selectedProfile.name}...`
: 'Select a voice profile above...'}
</span>
)}
</div>
</motion.div>
</div>
{/* Generate button */}
<button className="h-8 w-8 rounded-full bg-accent flex items-center justify-center shrink-0 shadow-lg">
<Sparkles className="h-3.5 w-3.5 text-accent-foreground" />
</button>
{phase === 'typing' ? (
<span className="text-foreground">
<TypewriterText text={typingText} />
</span>
) : phase === 'generating' ? (
<span className="text-muted-foreground/40">{typingText}</span>
) : (
<span>
{selectedProfile
? `Generate speech using ${selectedProfile.name}...`
: 'Select a voice profile above...'}
</span>
)}
</div>
</motion.div>
</div>
{/* Bottom selectors */}
<div className="flex items-center gap-1.5 mt-2">
<span className="text-[10px] px-2 py-1 rounded-full border border-border bg-card text-muted-foreground">
English
</span>
<span className="text-[10px] px-2 py-1 rounded-full border border-border bg-card text-muted-foreground">
Qwen3-TTS 1.7B
</span>
<span className="text-[10px] px-2 py-1 rounded-full border border-border bg-card text-muted-foreground flex items-center gap-1">
<Sparkles className="h-2.5 w-2.5" />
{effect || 'Effect'}
</span>
</div>
</motion.div>
</div>
{/* Generate button */}
<button className="h-8 w-8 rounded-full bg-accent flex items-center justify-center shrink-0 shadow-lg">
<Sparkles className="h-3.5 w-3.5 text-accent-foreground" />
</button>
</div>
{/* Bottom selectors */}
<div className="flex items-center gap-1.5 mt-2">
<span className="text-[10px] px-2 py-1 rounded-full border border-border bg-card text-muted-foreground">
English
</span>
<span className="text-[10px] px-2 py-1 rounded-full border border-border bg-card text-muted-foreground">
{engine}
</span>
<span className="text-[10px] px-2 py-1 rounded-full border border-border bg-card text-muted-foreground flex items-center gap-1">
<Sparkles className="h-2.5 w-2.5" />
{effect || 'Effect'}
</span>
</div>
</motion.div>
);
}
@@ -505,11 +508,20 @@ export function ControlUI() {
const [pageHidden, setPageHidden] = useState(false);
const containerRef = useRef<HTMLDivElement>(null);
const phaseRef = useRef(phase);
const profileCardRefs = useRef<Map<number, HTMLDivElement>>(new Map());
phaseRef.current = phase;
const step = DEMO_SCRIPT[cycle % DEMO_SCRIPT.length];
const selectedProfile = PROFILES[selectedIndex];
// Scroll to selected profile card
useEffect(() => {
const el = profileCardRefs.current.get(selectedIndex);
if (el) {
el.scrollIntoView({ behavior: 'smooth', block: 'nearest', inline: 'center' });
}
}, [selectedIndex]);
// Visibility detection
useEffect(() => {
const observer = new IntersectionObserver(([entry]) => setIsVisible(entry.isIntersecting), {
@@ -589,33 +601,83 @@ export function ControlUI() {
return (
<div ref={containerRef} className="relative z-20 mx-auto w-full max-w-6xl px-6">
{/* Unmute button */}
{/* Unmute button with handwritten hint */}
<div className="flex justify-end mb-3">
<button
onClick={() => setIsMuted(!isMuted)}
className="flex items-center gap-2 px-3 py-1.5 rounded-full border border-border bg-card/50 backdrop-blur text-xs text-muted-foreground hover:text-foreground transition-colors"
>
{isMuted ? (
<>
<Volume2 className="h-3.5 w-3.5" />
<span>Unmute</span>
</>
) : (
<>
<Volume2 className="h-3.5 w-3.5 text-accent" />
<span>Mute</span>
</>
<div className="relative">
{/* Handwritten hint — absolutely positioned above the button */}
{isMuted && (
<motion.div
className="absolute select-none pointer-events-none"
style={{ top: -30, right: 100 }}
initial={{ opacity: 0, y: 6 }}
animate={{ opacity: 1, y: 0 }}
transition={{ delay: 2, duration: 0.6, ease: 'easeOut' }}
>
<span
className="text-xl text-accent/80 whitespace-nowrap"
style={{
fontFamily: "'Caveat', 'Segoe Script', 'Comic Sans MS', cursive",
letterSpacing: '0.02em',
}}
>
try me!
</span>
{/* Curved arrow from text down-right toward the button */}
<svg
width="22"
height="11"
viewBox="0 0 80 40"
fill="none"
className="text-accent/70 absolute"
style={{ top: 14, left: 60 }}
aria-hidden="true"
>
<title>Arrow</title>
<path
d="M4 4 C20 4, 40 8, 55 20 C62 26, 66 32, 70 36"
stroke="currentColor"
strokeWidth="3"
strokeLinecap="round"
fill="none"
/>
<path
d="M58 42 L70 36 L64 22"
stroke="currentColor"
strokeWidth="3"
strokeLinecap="round"
strokeLinejoin="round"
transform="rotate(35, 70, 36)"
fill="none"
/>
</svg>
</motion.div>
)}
</button>
<button
onClick={() => {
unlockAudioContext();
setIsMuted(!isMuted);
}}
className="flex items-center gap-2 px-3 py-1.5 rounded-full border border-border bg-card/50 backdrop-blur text-xs text-muted-foreground hover:text-foreground transition-colors"
>
{isMuted ? (
<>
<Volume2 className="h-3.5 w-3.5" />
<span>Unmute</span>
</>
) : (
<>
<Volume2 className="h-3.5 w-3.5 text-accent" />
<span>Mute</span>
</>
)}
</button>
</div>
</div>
<div
className="overflow-hidden rounded-2xl border border-app-line bg-app-box shadow-[0_25px_60px_rgba(0,0,0,0.5),0_8px_20px_rgba(0,0,0,0.3)]"
style={{ height: 640 }}
>
<div className="flex h-full">
{/* ── Sidebar ───────────────────────────────────────────── */}
<div className="w-16 shrink-0 border-r border-app-line bg-sidebar flex flex-col items-center py-4 gap-4">
<div className="overflow-hidden rounded-2xl border border-app-line bg-app-box shadow-[0_25px_60px_rgba(0,0,0,0.5),0_8px_20px_rgba(0,0,0,0.3)] md:h-[640px]">
<div className="flex flex-col md:flex-row h-full">
{/* ── Sidebar (hidden on mobile) ─────────────────────────── */}
<div className="hidden md:flex w-16 shrink-0 border-r border-app-line bg-sidebar flex-col items-center py-4 gap-4">
{/* Logo */}
<div className="mb-1">
<div
@@ -658,11 +720,11 @@ export function ControlUI() {
</div>
{/* ── Main content ──────────────────────────────────────── */}
<div className="flex-1 flex min-w-0 relative">
{/* Left: Profiles */}
<div className="flex-1 flex flex-col min-w-0 relative">
<div className="flex-1 flex flex-col md:flex-row min-w-0 relative">
{/* Left: Profiles + Generate box */}
<div className="flex flex-col min-w-0 relative md:flex-1">
{/* Header */}
<div className="px-4 pt-6 pb-2 flex items-center justify-between relative z-10">
<div className="px-4 pt-4 md:pt-6 pb-2 flex items-center justify-between relative z-10">
<h2 className="text-base font-bold">Voicebox</h2>
<div className="flex items-center gap-1.5">
<button className="h-6 text-[10px] px-2.5 rounded-full border border-border bg-card text-muted-foreground flex items-center gap-1">
@@ -675,32 +737,58 @@ export function ControlUI() {
</div>
</div>
{/* Profile grid */}
<div className="flex-1 overflow-hidden px-4 pb-24">
<div className="grid grid-cols-3 gap-2 auto-rows-auto mt-1">
{/* Profile cards — horizontal scroll on mobile, 3-col grid on desktop */}
<div className="px-4">
{/* Mobile: horizontal scroll strip */}
<div className="flex gap-2 overflow-x-auto pb-2 md:hidden">
{PROFILES.map((profile, i) => (
<div
key={profile.name}
className="shrink-0 w-[140px]"
ref={(el) => {
if (el) profileCardRefs.current.set(i, el);
}}
>
<ProfileCard
profile={profile}
selected={i === selectedIndex}
selecting={phase === 'selecting'}
/>
</div>
))}
</div>
{/* Desktop: 3-col grid */}
<div className="hidden md:grid grid-cols-3 gap-2 mt-1 pb-24">
{PROFILES.map((profile, i) => (
<ProfileCard
key={profile.name}
profile={profile}
selected={i === selectedIndex}
selecting={phase === 'selecting'}
cardRef={(el: HTMLDivElement | null) => {
if (el) profileCardRefs.current.set(i, el);
}}
/>
))}
</div>
</div>
{/* Floating generate box */}
<FloatingGenerateBox
phase={phase}
typingText={step.text}
selectedProfile={selectedProfile}
effect={step.effect}
/>
{/* Floating generate box — desktop: absolute overlay, mobile: inline */}
<div className="px-3 pt-2 pb-3 md:pt-0 md:absolute md:left-3 md:right-3 md:bottom-[117px] md:z-20 md:pb-0">
<FloatingGenerateBox
phase={phase}
typingText={step.text}
selectedProfile={selectedProfile}
engine={step.engine}
effect={step.effect}
/>
</div>
</div>
{/* Right: History */}
<div className="w-[48%] shrink-0 flex flex-col min-w-0">
<div className="flex-1 overflow-hidden px-3 pt-6 pb-3">
{/* Right/Below: History */}
<div className="md:w-[48%] shrink-0 flex flex-col min-w-0 border-t md:border-t-0 border-app-line">
<div className="max-h-[360px] md:max-h-none flex-1 overflow-hidden px-3 pt-3 md:pt-6 pb-3">
<div className="flex flex-col gap-2">
{generations.map((gen) => {
const isThisNew = gen.id === newGenId;
+511 -134
View File
@@ -1,8 +1,8 @@
'use client';
import { motion } from 'framer-motion';
import { AudioLines, Cloud, Layers, MessageSquareText, Mic, Monitor } from 'lucide-react';
import { useEffect, useRef, useState } from 'react';
import { AudioLines, Cloud, MessageSquareText, Mic, Sparkles, TextCursorInput } from 'lucide-react';
import { useEffect, useMemo, useRef, useState } from 'react';
// ─── Lazy load wrapper ──────────────────────────────────────────────────────
@@ -111,122 +111,435 @@ function VoiceCloningAnimation() {
);
}
// ─── Animation: Stories Editor ───────────────────────────────────────────────
// ─── Mini waveform for clips ────────────────────────────────────────────────
// Fixed-width dense waveform that overflows — the clip container clips it.
// This way resizing a clip just reveals/hides bars instead of re-rendering.
function StoriesAnimation() {
const [activeTrack, setActiveTrack] = useState(0);
const tracks = [
{
name: 'Narrator',
color: '#ac8a2b',
clips: [
{ w: '45%', x: '5%' },
{ w: '30%', x: '60%' },
],
},
{
name: 'Character A',
color: '#3b82f6',
clips: [
{ w: '25%', x: '15%' },
{ w: '35%', x: '50%' },
],
},
{ name: 'Character B', color: '#8b5cf6', clips: [{ w: '20%', x: '30%' }] },
];
const WAVEFORM_BAR_COUNT = 60;
useEffect(() => {
const interval = setInterval(() => {
setActiveTrack((p) => (p + 1) % tracks.length);
}, 2200);
return () => clearInterval(interval);
}, [tracks.length]);
function MiniWaveform({ seed, color }: { seed: number; color: string }) {
// Deterministic pseudo-random waveform that looks like real speech audio.
// Uses layered noise at different frequencies for natural envelope + detail.
const bars = useMemo(() => {
// Seeded pseudo-random number generator (deterministic per seed)
let s = seed * 9301 + 49297;
const rand = () => {
s = (s * 16807 + 0) % 2147483647;
return s / 2147483647;
};
// Pre-generate random values
const r = Array.from({ length: WAVEFORM_BAR_COUNT }, () => rand());
return Array.from({ length: WAVEFORM_BAR_COUNT }, (_, i) => {
const t = i / WAVEFORM_BAR_COUNT;
// Slow envelope — broad amplitude shape (words / phrases)
const envelope =
0.3 +
0.35 *
Math.sin(t * Math.PI * (2 + (seed % 3))) *
Math.sin(t * Math.PI * (1.3 + seed * 0.7)) +
0.2 * Math.sin(t * Math.PI * (4.7 + seed * 1.3));
// Medium variation — syllable-level bumps
const mid = 0.15 * Math.sin(i * 0.8 + seed * 3.1) * Math.cos(i * 1.3 + seed);
// High-frequency noise — individual sample jitter
const noise = (r[i] - 0.5) * 0.25;
// Combine and clamp
const raw = envelope + mid + noise;
return Math.max(0.06, Math.min(1, raw));
});
}, [seed]);
return (
<div className="h-40 w-full flex flex-col justify-center overflow-hidden rounded-md bg-app-darkerBox/50 p-4 gap-2">
{tracks.map((track, i) => (
<motion.div
key={track.name}
className="flex items-center gap-2 h-8 rounded border px-2"
animate={{
borderColor: i === activeTrack ? `${track.color}40` : 'rgba(255,255,255,0.06)',
backgroundColor: i === activeTrack ? `${track.color}08` : 'rgba(255,255,255,0.02)',
<div className="flex items-center h-full overflow-hidden">
{bars.map((h, i) => (
<div
key={`w-${seed}-${i}`}
className="shrink-0 rounded-full opacity-50"
style={{
width: 2,
marginRight: 1,
height: `${h * 100}%`,
backgroundColor: color,
}}
transition={{ duration: 0.3 }}
>
<span
className="text-[8px] w-14 shrink-0 truncate"
style={{ color: i === activeTrack ? track.color : 'rgba(255,255,255,0.3)' }}
>
{track.name}
</span>
<div className="flex-1 relative h-4">
{track.clips.map((clip, j) => (
<motion.div
key={j}
className="absolute h-full rounded-sm"
style={{
left: clip.x,
width: clip.w,
backgroundColor:
i === activeTrack ? `${track.color}30` : 'rgba(255,255,255,0.04)',
borderLeft: `2px solid ${i === activeTrack ? track.color : 'rgba(255,255,255,0.1)'}`,
}}
transition={{ duration: 0.3 }}
/>
))}
</div>
</motion.div>
/>
))}
</div>
);
}
// ─── Animation: Multi-Sample ────────────────────────────────────────────────
// ─── Animation: Stories Editor ───────────────────────────────────────────────
function MultiSampleAnimation() {
const [active, setActive] = useState(0);
const samples = [
{ label: 'interview_clip.wav', dur: '12.4s', quality: 0.92 },
{ label: 'podcast_intro.wav', dur: '8.1s', quality: 0.88 },
{ label: 'narration_take3.wav', dur: '15.7s', quality: 0.95 },
{ label: 'casual_chat.wav', dur: '6.2s', quality: 0.85 },
// Clip shape: id, profile, track, left (px out of 220), width (px), waveform seed
type DemoClip = { id: string; profile: string; track: number; x: number; w: number; seed: number };
const INITIAL_CLIPS: DemoClip[] = [
{ id: 'n1', profile: 'Morgan', track: 0, x: 4, w: 70, seed: 1 },
{ id: 'n2', profile: 'Morgan', track: 0, x: 135, w: 35, seed: 2 },
{ id: 'a1', profile: 'Scarlett', track: 1, x: 25, w: 40, seed: 3 },
{ id: 'a2', profile: 'Scarlett', track: 1, x: 120, w: 35, seed: 4 },
{ id: 'b1', profile: 'Jarvis', track: 2, x: 70, w: 45, seed: 5 },
];
// Timeline width the clips live inside
const TL_W = 220;
// Each action returns a new clips array (or modifies in place)
type Action = { label: string; apply: (clips: DemoClip[]) => DemoClip[] };
const ACTIONS: Action[] = [
// 0 — move Jarvis clip earlier
{ label: 'Move clip', apply: (c) => c.map((cl) => (cl.id === 'b1' ? { ...cl, x: 55 } : cl)) },
// 1 — split Morgan's first clip into two with visible gap
{
label: 'Split clip',
apply: (c) => {
// Idempotent: if n1b already exists, the split already happened
if (c.some((cl) => cl.id === 'n1b')) return c;
const clip = c.find((cl) => cl.id === 'n1');
if (!clip) return c;
const leftW = 25;
const gap = 8;
const rightW = clip.w - leftW - gap;
return [
...c.filter((cl) => cl.id !== 'n1'),
{ ...clip, w: leftW, id: 'n1' },
{
id: 'n1b',
profile: clip.profile,
track: clip.track,
x: clip.x + leftW + gap,
w: rightW,
seed: 6,
},
];
},
},
// 2 — trim Scarlett's second clip shorter
{ label: 'Trim clip', apply: (c) => c.map((cl) => (cl.id === 'a2' ? { ...cl, w: 25 } : cl)) },
// 3 — duplicate Jarvis to track 0
{
label: 'Duplicate',
apply: (c) => {
// Idempotent: if b1d already exists, the duplicate already happened
if (c.some((cl) => cl.id === 'b1d')) return c;
const clip = c.find((cl) => cl.id === 'b1');
if (!clip) return c;
return [...c, { ...clip, id: 'b1d', track: 0, x: 180, w: 35, seed: 7 }];
},
},
// 4 — reset
{ label: '', apply: () => INITIAL_CLIPS },
];
function StoriesAnimation() {
const [clips, setClips] = useState<DemoClip[]>(INITIAL_CLIPS);
const [actionIndex, setActionIndex] = useState(-1);
const [playheadX, setPlayheadX] = useState(0);
const [selectedId, setSelectedId] = useState<string | null>(null);
const playheadRef = useRef<ReturnType<typeof requestAnimationFrame>>(0);
// Animate the playhead continuously
useEffect(() => {
let start: number | null = null;
const speed = 12; // px per second
const animate = (ts: number) => {
if (start === null) start = ts;
const elapsed = (ts - start) / 1000;
setPlayheadX((elapsed * speed) % TL_W);
playheadRef.current = requestAnimationFrame(animate);
};
playheadRef.current = requestAnimationFrame(animate);
return () => cancelAnimationFrame(playheadRef.current);
}, []);
// Step through actions
useEffect(() => {
const interval = setInterval(() => {
setActionIndex((prev) => {
const next = (prev + 1) % ACTIONS.length;
setClips((current) => ACTIONS[next].apply(current));
// Highlight the clip being acted on
if (next === 0) setSelectedId('b1');
else if (next === 1) setSelectedId('n1');
else if (next === 2) setSelectedId('a2');
else if (next === 3) setSelectedId('b1');
else setSelectedId(null);
return next;
});
}, 2600);
return () => clearInterval(interval);
}, []);
const trackLabels = ['1', '0', '-1'];
const timeMarkers = [0, 2, 4, 6, 8];
const accentColor = 'hsl(43 50% 45%)';
const accentFg = 'hsl(30 10% 94%)';
return (
<div className="h-40 w-full flex flex-col overflow-hidden rounded-md bg-app-darkerBox/50">
{/* Toolbar */}
<div className="flex items-center gap-1.5 px-2 py-1 border-b border-app-line bg-app-darkBox/60 shrink-0">
<div className="w-1.5 h-1.5 rounded-full bg-ink-faint/40" />
<div className="flex items-center gap-1">
<div className="w-4 h-4 rounded flex items-center justify-center bg-app-button">
<div className="border-l-[4px] border-l-ink-faint border-t-[3px] border-t-transparent border-b-[3px] border-b-transparent ml-0.5" />
</div>
<div className="w-4 h-4 rounded flex items-center justify-center bg-app-button">
<div className="w-2 h-2 rounded-sm bg-ink-faint/60" />
</div>
</div>
<span className="text-[8px] text-ink-faint font-mono ml-1 tabular-nums">0:03 / 0:10</span>
<div className="flex-1" />
{actionIndex >= 0 && actionIndex < ACTIONS.length - 1 && (
<motion.span
key={actionIndex}
className="text-[7px] font-medium px-1.5 py-0.5 rounded-full"
style={{
backgroundColor: `${accentColor.replace(')', ' / 0.15)')}`,
color: accentColor,
}}
initial={{ opacity: 0, y: 3 }}
animate={{ opacity: 1, y: 0 }}
exit={{ opacity: 0 }}
transition={{ duration: 0.25 }}
>
{ACTIONS[actionIndex].label}
</motion.span>
)}
<div className="flex items-center gap-0.5">
<span className="text-[7px] text-ink-faint">Zoom</span>
<div className="w-3 h-3 rounded flex items-center justify-center bg-app-button text-[8px] text-ink-faint">
-
</div>
<div className="w-3 h-3 rounded flex items-center justify-center bg-app-button text-[8px] text-ink-faint">
+
</div>
</div>
</div>
{/* Timeline */}
<div className="flex flex-1 min-h-0">
{/* Track labels sidebar */}
<div className="w-7 shrink-0 border-r border-app-line bg-app-darkBox/30 flex flex-col">
<div className="h-5 border-b border-app-line" />
{trackLabels.map((label) => (
<div
key={label}
className="flex-1 flex items-center justify-center border-b border-app-line"
>
<span className="text-[7px] text-ink-faint select-none">{label}</span>
</div>
))}
</div>
{/* Tracks area */}
<div className="flex-1 relative overflow-hidden flex flex-col">
{/* Time ruler */}
<div className="h-5 shrink-0 border-b border-app-line bg-app-darkBox/20 relative">
{timeMarkers.map((t) => (
<div
key={`tm-${t}`}
className="absolute top-0 h-full flex flex-col justify-end pb-0.5"
style={{ left: `${(t / 10) * 100}%` }}
>
<div className="h-1.5 w-px bg-app-line" />
<span className="text-[7px] text-ink-faint ml-0.5 select-none">{`0:0${t}`}</span>
</div>
))}
</div>
{/* Track rows + clips — same parent so percentages match */}
<div className="flex-1 relative min-h-0">
{/* Track rows background */}
{trackLabels.map((label, i) => (
<div
key={`bg-${label}`}
className="border-b border-app-line absolute left-0 right-0"
style={{
height: `${100 / 3}%`,
top: `${(i * 100) / 3}%`,
backgroundColor: i % 2 === 0 ? 'transparent' : 'rgba(255,255,255,0.01)',
}}
/>
))}
{/* Clips */}
{clips.map((clip) => {
const trackIdx = clip.track;
const isSelected = clip.id === selectedId;
const clipTop = `calc(${(trackIdx * 100) / 3}% + 2px)`;
const clipHeight = `calc(${100 / 3}% - 4px)`;
return (
<motion.div
key={clip.id}
className="absolute rounded overflow-hidden"
initial={false}
style={{
height: clipHeight,
left: `${(clip.x / TL_W) * 100}%`,
width: `${(clip.w / TL_W) * 100}%`,
top: clipTop,
}}
animate={{
left: `${(clip.x / TL_W) * 100}%`,
width: `${(clip.w / TL_W) * 100}%`,
top: clipTop,
}}
transition={{ type: 'spring', stiffness: 200, damping: 25 }}
>
<div
className="w-full h-full rounded overflow-hidden flex flex-col"
style={{
backgroundColor: isSelected ? 'hsl(43 50% 45%)' : 'hsl(43 45% 40%)',
boxShadow: isSelected
? 'inset 0 0 0 1px hsl(43 50% 55%), 0 0 0 1px hsl(30 10% 94% / 0.4)'
: 'inset 0 0 0 1px hsl(30 10% 94% / 0.1)',
}}
>
{/* Profile label — scaled to bypass browser min font size */}
<div className="shrink-0 relative" style={{ height: 9 }}>
<span
className="text-[10px] font-medium leading-none absolute top-0 left-0.5 origin-top-left opacity-80 whitespace-nowrap"
style={{ color: accentFg, transform: 'scale(0.75)' }}
>
{clip.profile}
</span>
</div>
{/* Waveform — absolutely positioned so it never affects clip width */}
<div className="absolute left-0 right-0 bottom-0" style={{ top: 9 }}>
<MiniWaveform seed={clip.seed} color={accentFg} />
</div>
</div>
{/* Trim handles on selected */}
{isSelected && (
<>
<div
className="absolute left-0 top-0 bottom-0 w-1 rounded-l"
style={{ backgroundColor: 'hsl(30 10% 94% / 0.25)' }}
/>
<div
className="absolute right-0 top-0 bottom-0 w-1 rounded-r"
style={{ backgroundColor: 'hsl(30 10% 94% / 0.25)' }}
/>
</>
)}
</motion.div>
);
})}
{/* Playhead */}
<motion.div
className="absolute top-0 bottom-0 w-[2px] rounded-full z-20 pointer-events-none"
style={{ backgroundColor: accentColor }}
animate={{ left: `${(playheadX / TL_W) * 100}%` }}
transition={{ duration: 0.05, ease: 'linear' }}
>
<div
className="absolute -top-0.5 left-1/2 -translate-x-1/2 w-2 h-2 rounded-full"
style={{ backgroundColor: accentColor }}
/>
</motion.div>
</div>
</div>
</div>
</div>
);
}
// ─── Animation: Effects Pipeline ────────────────────────────────────────────
function EffectsAnimation() {
const [activeEffect, setActiveEffect] = useState(0);
const effects = [
{ name: 'Pitch Shift', param: '-3 semitones', color: '#3b82f6' },
{ name: 'Reverb', param: 'Room 0.7', color: '#8b5cf6' },
{ name: 'Compressor', param: '-15 dB', color: '#ec4899' },
{ name: 'Low-Pass', param: '6000 Hz', color: '#14b8a6' },
];
// Waveform bars — original shape
const rawBars = [0.3, 0.6, 0.8, 0.5, 0.9, 0.4, 0.7, 0.3, 0.6, 0.5, 0.8, 0.4, 0.7, 0.9, 0.3];
useEffect(() => {
const interval = setInterval(() => {
setActive((p) => (p + 1) % samples.length);
}, 2000);
setActiveEffect((p) => (p + 1) % effects.length);
}, 2200);
return () => clearInterval(interval);
}, [samples.length]);
}, [effects.length]);
return (
<div className="h-40 w-full flex flex-col justify-center overflow-hidden rounded-md bg-app-darkerBox/50 p-4 gap-1.5">
{samples.map((s, i) => (
<motion.div
key={s.label}
className="flex items-center gap-2 px-2 py-1.5 rounded border text-[9px]"
animate={{
borderColor: i === active ? 'hsl(43 50% 45% / 0.4)' : 'rgba(255,255,255,0.06)',
backgroundColor: i === active ? 'hsl(43 50% 45% / 0.06)' : 'rgba(255,255,255,0.02)',
}}
transition={{ duration: 0.3 }}
>
<span
className={`flex-1 font-mono truncate ${i === active ? 'text-accent' : 'text-ink-faint'}`}
>
{s.label}
</span>
<span className="text-ink-faint shrink-0">{s.dur}</span>
<div className="w-10 h-1 rounded-full bg-app-line shrink-0 overflow-hidden">
<div className="h-40 w-full flex flex-col items-center justify-center overflow-hidden rounded-md bg-app-darkerBox/50 p-4 gap-3">
{/* Effects chain */}
<div className="flex items-center gap-1">
{effects.map((fx, i) => (
<div key={fx.name} className="flex items-center gap-1">
<motion.div
className="h-full rounded-full bg-accent"
animate={{ width: i === active ? `${s.quality * 100}%` : '0%' }}
transition={{ duration: 0.5, delay: i === active ? 0.2 : 0 }}
/>
className="text-[8px] px-2 py-0.5 rounded-full border font-medium"
animate={{
borderColor: i <= activeEffect ? `${fx.color}60` : 'rgba(255,255,255,0.06)',
backgroundColor: i <= activeEffect ? `${fx.color}15` : 'rgba(255,255,255,0.02)',
color: i <= activeEffect ? fx.color : 'rgba(255,255,255,0.3)',
}}
transition={{ duration: 0.3 }}
>
{fx.name}
</motion.div>
{i < effects.length - 1 && (
<motion.span
className="text-[8px]"
animate={{
color: i < activeEffect ? 'rgba(255,255,255,0.3)' : 'rgba(255,255,255,0.08)',
}}
transition={{ duration: 0.3 }}
>
&rarr;
</motion.span>
)}
</div>
</motion.div>
))}
))}
</div>
{/* Waveform that morphs as effects are applied */}
<div className="flex items-center gap-[2px] h-10 w-full max-w-[200px] justify-center">
{rawBars.map((h, i) => {
// Each effect stage progressively transforms the shape
const shifted = activeEffect >= 0 ? h * (0.7 + 0.3 * Math.sin(i * 0.8)) : h;
const dampened = activeEffect >= 1 ? shifted * (0.6 + 0.4 * Math.cos(i * 0.3)) : shifted;
const compressed = activeEffect >= 2 ? 0.3 + dampened * 0.5 : dampened;
const filtered = activeEffect >= 3 ? compressed * (1 - i * 0.03) : compressed;
const finalH = Math.max(0.08, Math.min(1, filtered));
return (
<motion.div
key={`bar-${i}`}
className="w-[3px] rounded-full"
animate={{
height: `${finalH * 100}%`,
backgroundColor: effects[activeEffect].color,
}}
transition={{
height: { duration: 0.5, delay: i * 0.02, ease: 'easeInOut' },
backgroundColor: { duration: 0.4 },
}}
/>
);
})}
</div>
{/* Active effect detail */}
<motion.div
className="text-[9px] font-mono text-ink-faint"
key={activeEffect}
initial={{ opacity: 0, y: 4 }}
animate={{ opacity: 1, y: 0 }}
transition={{ duration: 0.3 }}
>
{effects[activeEffect].name}: {effects[activeEffect].param}
</motion.div>
</div>
);
}
@@ -332,51 +645,115 @@ function TranscriptionAnimation() {
);
}
// ─── Animation: Cross-Platform ──────────────────────────────────────────────
// ─── Animation: Unlimited Length ─────────────────────────────────────────────
function CrossPlatformAnimation() {
const [active, setActive] = useState(0);
const platforms = [
{ name: 'macOS', icon: '🍎', detail: 'Metal acceleration' },
{ name: 'Windows', icon: '🪟', detail: 'CUDA acceleration' },
{ name: 'Linux', icon: '🐧', detail: 'CUDA acceleration' },
function UnlimitedLengthAnimation() {
const [phase, setPhase] = useState(0);
const chunks = [
'The morning sun crept over the mountains, casting long shadows across the valley below.',
'Birds stirred in the canopy, their songs weaving through the cool air like threads of gold.',
'Far below, a river wound its way through ancient stones, carrying whispers of the night.',
];
useEffect(() => {
const interval = setInterval(() => {
setActive((p) => (p + 1) % platforms.length);
setPhase((p) => (p + 1) % 4); // 0-2 = processing chunks, 3 = crossfade/done
}, 2000);
return () => clearInterval(interval);
}, [platforms.length]);
}, []);
return (
<div className="h-40 w-full flex items-center justify-center overflow-hidden rounded-md bg-app-darkerBox/50 p-4">
<div className="flex gap-3">
{platforms.map((p, i) => (
<div className="h-40 w-full flex flex-col items-center justify-center overflow-hidden rounded-md bg-app-darkerBox/50 p-4 gap-2.5">
{/* Chunk pills */}
<div className="flex flex-col gap-1 w-full max-w-[220px]">
{chunks.map((chunk, i) => (
<motion.div
key={p.name}
className="flex flex-col items-center gap-2 px-3 py-2.5 rounded-lg border"
key={`chunk-${i}`}
className="flex items-center gap-1.5 px-2 py-1 rounded border text-[8px]"
animate={{
borderColor: i === active ? 'hsl(43 50% 45% / 0.4)' : 'rgba(255,255,255,0.06)',
backgroundColor: i === active ? 'hsl(43 50% 45% / 0.06)' : 'rgba(255,255,255,0.02)',
scale: i === active ? 1.05 : 1,
borderColor:
phase === 3
? 'hsl(43 50% 45% / 0.3)'
: i === phase
? 'hsl(43 50% 45% / 0.5)'
: i < phase
? 'rgba(255,255,255,0.12)'
: 'rgba(255,255,255,0.06)',
backgroundColor:
phase === 3
? 'hsl(43 50% 45% / 0.04)'
: i === phase
? 'hsl(43 50% 45% / 0.08)'
: i < phase
? 'rgba(255,255,255,0.04)'
: 'rgba(255,255,255,0.02)',
}}
transition={{ duration: 0.3 }}
transition={{ duration: 0.4 }}
>
<span className="text-lg">{p.icon}</span>
{/* Status indicator */}
<motion.div
className="w-1.5 h-1.5 rounded-full shrink-0"
animate={{
backgroundColor:
phase === 3
? 'hsl(43 50% 50%)'
: i === phase
? 'hsl(43 50% 50%)'
: i < phase
? 'rgba(255,255,255,0.3)'
: 'rgba(255,255,255,0.1)',
boxShadow:
i === phase && phase < 3 ? '0 0 6px hsl(43 50% 50%)' : '0 0 0px transparent',
}}
transition={{ duration: 0.3 }}
/>
<span
className={`text-[9px] font-medium ${i === active ? 'text-accent' : 'text-ink-faint'}`}
className={`truncate font-mono ${
phase === 3 || i <= phase ? 'text-ink-dull' : 'text-ink-faint/50'
}`}
>
{p.name}
</span>
<span
className={`text-[7px] font-mono ${i === active ? 'text-ink-dull' : 'text-ink-faint/50'}`}
>
{p.detail}
{chunk}
</span>
</motion.div>
))}
</div>
{/* Crossfade / result bar */}
<div className="flex items-center gap-1 w-full max-w-[220px]">
{chunks.map((_, i) => (
<motion.div
key={`seg-${i}`}
className="h-1.5 flex-1 rounded-full"
animate={{
backgroundColor:
phase === 3
? 'hsl(43 50% 45%)'
: i < phase
? 'rgba(255,255,255,0.2)'
: i === phase
? 'hsl(43 50% 45% / 0.5)'
: 'rgba(255,255,255,0.06)',
}}
transition={{ duration: 0.4 }}
/>
))}
</div>
{/* Status text */}
<motion.div
className="text-[9px] font-mono"
key={phase}
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
transition={{ duration: 0.3 }}
>
<span className={phase === 3 ? 'text-accent' : 'text-ink-faint'}>
{phase < 3
? `generating chunk ${phase + 1} of ${chunks.length}...`
: 'crossfaded & ready'}
</span>
</motion.div>
</div>
);
}
@@ -387,7 +764,7 @@ const FEATURES = [
{
title: 'Near-Perfect Voice Cloning',
description:
'Powered by Qwen3-TTS for exceptional voice quality. Clone any voice from a few seconds of audio with natural intonation and emotion.',
'Multiple TTS engines for exceptional voice quality. Clone any voice from a few seconds of audio with natural intonation and emotion.',
icon: Mic,
animation: VoiceCloningAnimation,
},
@@ -399,16 +776,16 @@ const FEATURES = [
animation: StoriesAnimation,
},
{
title: 'Multi-Sample Support',
title: 'Audio Effects Pipeline',
description:
'Combine multiple voice samples for higher quality results. More samples means more natural-sounding speech synthesis.',
icon: Layers,
animation: MultiSampleAnimation,
'Apply pitch shift, reverb, delay, compression, and more — then save as presets. Preview effects live and set defaults per voice profile.',
icon: Sparkles,
animation: EffectsAnimation,
},
{
title: 'Local or Remote',
description:
'Run GPU inference locally with Metal or CUDA, or connect to a remote machine. One-click server setup with automatic discovery.',
'Run GPU inference locally with Metal, CUDA, ROCm, Intel Arc, or DirectML — or connect to a remote machine. One-click server setup with automatic discovery.',
icon: Cloud,
animation: LocalRemoteAnimation,
},
@@ -420,11 +797,11 @@ const FEATURES = [
animation: TranscriptionAnimation,
},
{
title: 'Cross-Platform',
title: 'Unlimited Generation Length',
description:
'Available for macOS, Windows, and Linux. No Python installation required — everything is bundled.',
icon: Monitor,
animation: CrossPlatformAnimation,
'Generate up to 50,000 characters in one go. Text is auto-split at sentence boundaries, generated per-chunk, and crossfaded seamlessly.',
icon: TextCursorInput,
animation: UnlimitedLengthAnimation,
},
];
+48 -44
View File
@@ -1,6 +1,6 @@
'use client';
import { Pause, Play, Repeat, Volume2, VolumeX, X } from 'lucide-react';
import { Pause, Play, Repeat, Volume2, VolumeX } from 'lucide-react';
import { useCallback, useEffect, useRef, useState } from 'react';
import WaveSurfer from 'wavesurfer.js';
@@ -10,6 +10,26 @@ function formatDuration(seconds: number): string {
return `${m}:${s.toString().padStart(2, '0')}`;
}
// Unlock Web Audio on iOS Safari — must be called from a user gesture (click/tap)
let audioContextUnlocked = false;
export function unlockAudioContext() {
if (audioContextUnlocked) return;
try {
const ctx = new (
window.AudioContext ||
(window as unknown as { webkitAudioContext: typeof AudioContext }).webkitAudioContext
)();
const buffer = ctx.createBuffer(1, 1, 22050);
const source = ctx.createBufferSource();
source.buffer = buffer;
source.connect(ctx.destination);
source.start(0);
audioContextUnlocked = true;
} catch {
// Silently fail — non-Safari browsers don't need this
}
}
interface LandingAudioPlayerProps {
audioUrl: string;
title: string;
@@ -145,24 +165,23 @@ export function LandingAudioPlayer({
if (!ws || !isReady) return;
if (playing) {
// Resume the AudioContext first (required for iOS Safari after unlock)
const backend = ws.getMediaElement();
if (backend && 'context' in backend) {
const ctx = (backend as unknown as { context: AudioContext }).context;
if (ctx?.state === 'suspended') ctx.resume();
}
ws.play()
.then(() => {
console.log(
'[Player] play succeeded, isPlaying:',
ws.isPlaying(),
'currentTime:',
ws.getCurrentTime(),
);
setTimeout(() => {
console.log(
'[Player] 1s later, isPlaying:',
ws.isPlaying(),
'currentTime:',
ws.getCurrentTime(),
);
}, 1000);
console.log('[Player] play succeeded');
})
.catch((e) => console.error('[Player] play failed', e));
.catch((e: Error) => {
if (e.name === 'NotAllowedError') {
console.warn('[Player] Autoplay blocked by browser — waiting for user gesture');
} else {
console.error('[Player] play failed', e);
}
});
} else {
ws.pause();
}
@@ -180,34 +199,27 @@ export function LandingAudioPlayer({
wavesurferRef.current.playPause();
}, []);
const handleClose = useCallback(() => {
if (wavesurferRef.current) {
wavesurferRef.current.pause();
}
setIsPlaying(false);
onClose();
}, [onClose]);
return (
<div className="absolute bottom-0 left-0 right-0 border-t border-border bg-background/95 backdrop-blur supports-backdrop-filter:bg-background/60 z-30">
<div className="px-4 py-3">
<div className="flex items-center gap-4">
<div className="px-4 py-3 flex flex-col md:flex-row md:items-center gap-2 md:gap-4">
{/* Waveform — full width row on mobile, inline on desktop */}
<div className="min-w-0 min-h-[60px] md:min-h-[80px] md:flex-1 md:order-2">
<div ref={waveformRef} className="w-full h-full min-h-[60px] md:min-h-[80px]" />
</div>
{/* Controls row */}
<div className="flex items-center gap-3 md:contents">
{/* Play/Pause */}
<button
onClick={handlePlayPause}
disabled={!isReady}
className="h-10 w-10 rounded-full flex items-center justify-center hover:bg-muted shrink-0 disabled:opacity-50"
className="h-10 w-10 rounded-full flex items-center justify-center hover:bg-muted shrink-0 disabled:opacity-50 md:order-1"
>
{isPlaying ? <Pause className="h-5 w-5" /> : <Play className="h-5 w-5 ml-0.5" />}
</button>
{/* Waveform */}
<div className="flex-1 min-w-0 flex flex-col gap-1">
<div ref={waveformRef} className="w-full min-h-[80px]" />
</div>
{/* Time */}
<div className="flex items-center gap-1 text-sm text-muted-foreground shrink-0">
<div className="flex items-center gap-1 text-sm text-muted-foreground shrink-0 md:order-3">
<span className="font-mono text-xs">{formatDuration(currentTime)}</span>
<span className="text-xs">/</span>
<span className="font-mono text-xs">{formatDuration(duration)}</span>
@@ -215,7 +227,7 @@ export function LandingAudioPlayer({
{/* Title */}
{title && (
<div className="text-sm font-medium truncate max-w-[200px] shrink-0 hidden lg:block">
<div className="text-sm font-medium truncate max-w-[200px] shrink-0 hidden lg:block md:order-4">
{title}
</div>
)}
@@ -223,7 +235,7 @@ export function LandingAudioPlayer({
{/* Loop */}
<button
onClick={() => setIsLooping(!isLooping)}
className={`h-8 w-8 flex items-center justify-center rounded-sm shrink-0 hover:bg-muted ${
className={`h-8 w-8 flex items-center justify-center rounded-sm shrink-0 hover:bg-muted md:order-5 ${
isLooping ? 'text-foreground' : 'text-muted-foreground'
}`}
>
@@ -231,7 +243,7 @@ export function LandingAudioPlayer({
</button>
{/* Volume */}
<div className="flex items-center gap-2 shrink-0 w-[120px]">
<div className="flex items-center gap-2 shrink-0 w-[120px] md:order-6">
<button
onClick={() => setVolume(volume > 0 ? 0 : 0.75)}
className="h-8 w-8 flex items-center justify-center hover:bg-muted rounded-sm"
@@ -251,14 +263,6 @@ export function LandingAudioPlayer({
className="flex-1 h-1 appearance-none bg-muted rounded-full accent-foreground cursor-pointer [&::-webkit-slider-thumb]:appearance-none [&::-webkit-slider-thumb]:h-3 [&::-webkit-slider-thumb]:w-3 [&::-webkit-slider-thumb]:rounded-full [&::-webkit-slider-thumb]:bg-foreground"
/>
</div>
{/* Close */}
<button
onClick={handleClose}
className="h-8 w-8 flex items-center justify-center hover:bg-muted rounded-sm shrink-0"
>
<X className="h-5 w-5 text-muted-foreground" />
</button>
</div>
</div>
</div>
+31 -2
View File
@@ -2,9 +2,34 @@
import { Github } from 'lucide-react';
import Image from 'next/image';
import { useEffect, useState } from 'react';
import { GITHUB_REPO } from '@/lib/constants';
function formatStarCount(count: number): string {
if (count >= 1000) {
const k = count / 1000;
return k % 1 === 0 ? `${k}k` : `${k.toFixed(1)}k`;
}
return count.toString();
}
export function Navbar() {
const [starCount, setStarCount] = useState<number | null>(null);
useEffect(() => {
fetch('/api/stars')
.then((res) => {
if (!res.ok) throw new Error('Failed to fetch stars');
return res.json();
})
.then((data) => {
if (typeof data.count === 'number') setStarCount(data.count);
})
.catch((error) => {
console.error('Failed to fetch star count:', error);
});
}, []);
return (
<nav className="fixed inset-x-0 top-0 z-50 border-b border-border/50 bg-background/80 backdrop-blur-xl">
<div className="mx-auto flex max-w-7xl items-center justify-between px-6 py-3">
@@ -50,8 +75,12 @@ export function Navbar() {
className="flex items-center gap-2 rounded-lg border border-border/60 bg-card/60 px-3 py-1.5 text-sm text-muted-foreground transition-colors hover:text-foreground hover:border-border"
>
<Github className="h-4 w-4" />
<span className="hidden sm:inline">Star on GitHub</span>
<span className="sm:hidden">GitHub</span>
<span className="text-[13px] font-medium">Star</span>
{starCount !== null && (
<span className="border-l border-border/60 pl-2 text-[13px] font-semibold text-foreground">
{formatStarCount(starCount)}
</span>
)}
</a>
</div>
</nav>
+479
View File
@@ -0,0 +1,479 @@
'use client';
import { AnimatePresence, motion } from 'framer-motion';
import { Mic, Monitor, Upload } from 'lucide-react';
import { useEffect, useMemo, useState } from 'react';
// ─── Waveform bars generator ────────────────────────────────────────────────
function generateWaveformBars(count: number, seed: number): number[] {
const bars: number[] = [];
for (let i = 0; i < count; i++) {
const x = i / count;
// Speech-like envelope: ramp up, sustain, taper
const envelope = Math.sin(x * Math.PI) * 0.8 + 0.2;
// Layered pseudo-random noise
const n1 = Math.sin(seed * 127.1 + i * 43.7) * 0.5 + 0.5;
const n2 = Math.sin(seed * 269.5 + i * 17.3) * 0.3 + 0.5;
const n3 = Math.sin(seed * 53.9 + i * 97.1) * 0.2 + 0.5;
const noise = (n1 + n2 + n3) / 3;
bars.push(envelope * noise);
}
return bars;
}
// ─── Animated waveform background ───────────────────────────────────────────
function WaveformBackground({ active }: { active: boolean }) {
const bars = useMemo(() => generateWaveformBars(60, 42), []);
return (
<div className="absolute inset-0 pointer-events-none flex items-end justify-center overflow-hidden">
<div className="flex items-end gap-[2px] w-full h-full px-4 pb-4">
{bars.map((h, i) => {
const maxH = 120; // max bar height in px
const baseH = 4;
const activeH = baseH + h * maxH;
const idleH = baseH + h * maxH * 0.25;
return (
<motion.div
key={i}
className="flex-1 rounded-full bg-accent"
animate={{
opacity: active ? 0.35 : 0.1,
height: active ? [idleH, activeH, idleH * 1.5, activeH * 0.7, idleH] : idleH,
}}
transition={
active
? {
duration: 1.0 + (i % 5) * 0.12,
repeat: Infinity,
repeatType: 'mirror',
delay: (i % 7) * 0.04,
ease: 'easeInOut',
}
: { duration: 0.6 }
}
/>
);
})}
</div>
</div>
);
}
// ─── Tab content panels ─────────────────────────────────────────────────────
function UploadPanel() {
const [hasFile, setHasFile] = useState(false);
useEffect(() => {
// Simulate file drop after 2s
const t1 = setTimeout(() => setHasFile(true), 2000);
const t2 = setTimeout(() => setHasFile(false), 5000);
return () => {
clearTimeout(t1);
clearTimeout(t2);
};
}, []);
return (
<div
className={`relative flex flex-col items-center justify-center gap-3 p-6 border-2 rounded-lg min-h-[180px] transition-colors duration-300 ${
hasFile ? 'border-accent bg-accent/5' : 'border-dashed border-muted-foreground/25'
}`}
>
<AnimatePresence mode="wait">
{!hasFile ? (
<motion.div
key="idle"
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
exit={{ opacity: 0 }}
className="flex flex-col items-center gap-3"
>
<div className="h-10 px-5 rounded-md bg-accent text-accent-foreground flex items-center gap-2 text-sm font-medium">
<Upload className="h-4 w-4" />
Choose File
</div>
<p className="text-xs text-muted-foreground text-center">
Drag and drop an audio file, or click to browse.
<br />
Maximum duration: 30 seconds.
</p>
</motion.div>
) : (
<motion.div
key="file"
initial={{ opacity: 0, scale: 0.95 }}
animate={{ opacity: 1, scale: 1 }}
exit={{ opacity: 0 }}
className="flex flex-col items-center gap-3"
>
<div className="flex items-center gap-2">
<Upload className="h-4 w-4 text-accent" />
<span className="text-sm font-medium">sample-voice-clip.wav</span>
</div>
<div className="flex gap-2">
<div className="h-8 px-3 rounded-md border border-border flex items-center gap-1.5 text-xs text-muted-foreground">
<span>0:04</span>
</div>
<div className="h-8 px-3 rounded-md border border-border flex items-center gap-1.5 text-xs text-muted-foreground">
<Mic className="h-3 w-3" />
Transcribe
</div>
</div>
</motion.div>
)}
</AnimatePresence>
</div>
);
}
function RecordPanel() {
const [state, setState] = useState<'idle' | 'recording' | 'done'>('idle');
const [elapsed, setElapsed] = useState(0);
useEffect(() => {
const t1 = setTimeout(() => setState('recording'), 1500);
const t2 = setTimeout(() => setState('done'), 5500);
const t3 = setTimeout(() => {
setState('idle');
setElapsed(0);
}, 8000);
return () => {
clearTimeout(t1);
clearTimeout(t2);
clearTimeout(t3);
};
}, []);
// Timer
useEffect(() => {
if (state !== 'recording') return;
setElapsed(0);
const interval = setInterval(() => setElapsed((e) => e + 1), 1000);
return () => clearInterval(interval);
}, [state]);
const formatTime = (s: number) => `${Math.floor(s / 60)}:${(s % 60).toString().padStart(2, '0')}`;
return (
<div
className={`relative flex flex-col items-center justify-center gap-3 p-6 border-2 rounded-lg min-h-[180px] overflow-hidden transition-colors duration-300 ${
state === 'recording'
? 'border-accent bg-accent/5'
: state === 'done'
? 'border-accent bg-accent/5'
: 'border-dashed border-muted-foreground/25'
}`}
>
<WaveformBackground active={state === 'recording'} />
<AnimatePresence mode="wait">
{state === 'idle' && (
<motion.div
key="idle"
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
exit={{ opacity: 0 }}
className="relative z-10 flex flex-col items-center gap-3"
>
<div className="h-10 px-5 rounded-md bg-accent text-accent-foreground flex items-center gap-2 text-sm font-medium">
<Mic className="h-4 w-4" />
Start Recording
</div>
<p className="text-xs text-muted-foreground text-center">
Click to record from your microphone.
<br />
Maximum duration: 30 seconds.
</p>
</motion.div>
)}
{state === 'recording' && (
<motion.div
key="recording"
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
exit={{ opacity: 0 }}
className="relative z-10 flex flex-col items-center gap-3"
>
<div className="flex items-center gap-3">
<div className="h-3 w-3 rounded-full bg-accent animate-pulse" />
<span className="text-lg font-mono font-semibold">{formatTime(elapsed)}</span>
</div>
<div className="h-9 px-4 rounded-md bg-accent text-accent-foreground flex items-center gap-2 text-sm font-medium">
<div className="h-3 w-3 rounded-sm bg-accent-foreground" />
Stop Recording
</div>
<p className="text-xs text-muted-foreground">{formatTime(30 - elapsed)} remaining</p>
</motion.div>
)}
{state === 'done' && (
<motion.div
key="done"
initial={{ opacity: 0, scale: 0.95 }}
animate={{ opacity: 1, scale: 1 }}
exit={{ opacity: 0 }}
className="relative z-10 flex flex-col items-center gap-3"
>
<div className="flex items-center gap-2">
<Mic className="h-4 w-4 text-accent" />
<span className="text-sm font-medium">Recording complete</span>
</div>
<div className="flex gap-2">
<div className="h-8 px-3 rounded-md border border-border flex items-center gap-1.5 text-xs text-muted-foreground">
<span>0:04</span>
</div>
<div className="h-8 px-3 rounded-md border border-border flex items-center gap-1.5 text-xs text-muted-foreground">
<Mic className="h-3 w-3" />
Transcribe
</div>
</div>
</motion.div>
)}
</AnimatePresence>
</div>
);
}
function SystemPanel() {
const [state, setState] = useState<'idle' | 'capturing' | 'done'>('idle');
const [elapsed, setElapsed] = useState(0);
useEffect(() => {
const t1 = setTimeout(() => setState('capturing'), 1500);
const t2 = setTimeout(() => setState('done'), 5500);
const t3 = setTimeout(() => {
setState('idle');
setElapsed(0);
}, 8000);
return () => {
clearTimeout(t1);
clearTimeout(t2);
clearTimeout(t3);
};
}, []);
useEffect(() => {
if (state !== 'capturing') return;
setElapsed(0);
const interval = setInterval(() => setElapsed((e) => e + 1), 1000);
return () => clearInterval(interval);
}, [state]);
const formatTime = (s: number) => `${Math.floor(s / 60)}:${(s % 60).toString().padStart(2, '0')}`;
return (
<div
className={`relative flex flex-col items-center justify-center gap-3 p-6 border-2 rounded-lg min-h-[180px] overflow-hidden transition-colors duration-300 ${
state === 'capturing'
? 'border-accent bg-accent/5'
: state === 'done'
? 'border-accent bg-accent/5'
: 'border-dashed border-muted-foreground/25'
}`}
>
<WaveformBackground active={state === 'capturing'} />
<AnimatePresence mode="wait">
{state === 'idle' && (
<motion.div
key="idle"
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
exit={{ opacity: 0 }}
className="relative z-10 flex flex-col items-center gap-3"
>
<div className="h-10 px-5 rounded-md bg-accent text-accent-foreground flex items-center gap-2 text-sm font-medium">
<Monitor className="h-4 w-4" />
Start Capture
</div>
<p className="text-xs text-muted-foreground text-center">
Capture audio playing on your system.
<br />
Maximum duration: 30 seconds.
</p>
</motion.div>
)}
{state === 'capturing' && (
<motion.div
key="capturing"
initial={{ opacity: 0 }}
animate={{ opacity: 1 }}
exit={{ opacity: 0 }}
className="relative z-10 flex flex-col items-center gap-3"
>
<div className="flex items-center gap-3">
<div className="h-3 w-3 rounded-full bg-accent animate-pulse" />
<span className="text-lg font-mono font-semibold">{formatTime(elapsed)}</span>
</div>
<div className="h-9 px-4 rounded-md bg-accent text-accent-foreground flex items-center gap-2 text-sm font-medium">
<div className="h-3 w-3 rounded-sm bg-accent-foreground" />
Stop Capture
</div>
<p className="text-xs text-muted-foreground">{formatTime(30 - elapsed)} remaining</p>
</motion.div>
)}
{state === 'done' && (
<motion.div
key="done"
initial={{ opacity: 0, scale: 0.95 }}
animate={{ opacity: 1, scale: 1 }}
exit={{ opacity: 0 }}
className="relative z-10 flex flex-col items-center gap-3"
>
<div className="flex items-center gap-2">
<Monitor className="h-4 w-4 text-accent" />
<span className="text-sm font-medium">Capture complete</span>
</div>
<div className="flex gap-2">
<div className="h-8 px-3 rounded-md border border-border flex items-center gap-1.5 text-xs text-muted-foreground">
<span>0:04</span>
</div>
<div className="h-8 px-3 rounded-md border border-border flex items-center gap-1.5 text-xs text-muted-foreground">
<Mic className="h-3 w-3" />
Transcribe
</div>
</div>
</motion.div>
)}
</AnimatePresence>
</div>
);
}
// ─── Tab selector ───────────────────────────────────────────────────────────
const TABS = [
{ id: 'upload' as const, label: 'Upload', icon: Upload },
{ id: 'record' as const, label: 'Microphone', icon: Mic },
{ id: 'system' as const, label: 'System Audio', icon: Monitor },
];
type TabId = (typeof TABS)[number]['id'];
// ─── Main section ───────────────────────────────────────────────────────────
export function VoiceCreator() {
const [activeTab, setActiveTab] = useState<TabId>('record');
const [cycleKey, setCycleKey] = useState(0);
// Auto-cycle tabs
useEffect(() => {
const tabOrder: TabId[] = ['record', 'upload', 'system'];
let idx = tabOrder.indexOf(activeTab);
const interval = setInterval(() => {
idx = (idx + 1) % tabOrder.length;
setActiveTab(tabOrder[idx]);
setCycleKey((k) => k + 1);
}, 9000);
return () => clearInterval(interval);
}, [activeTab]);
return (
<section className="border-t border-border py-24">
<div className="mx-auto max-w-5xl px-6">
<div className="grid grid-cols-1 md:grid-cols-2 gap-12 md:gap-16 items-center">
{/* Left: Copy */}
<div>
<h2 className="text-3xl font-semibold tracking-tight text-foreground md:text-4xl mb-4">
Clone any voice in seconds
</h2>
<p className="text-muted-foreground mb-6">
Three ways to capture a voice sample. Upload a clip, record from your microphone, or
capture audio playing on your system. Voicebox clones the voice from as little as 3
seconds of audio.
</p>
<div className="space-y-3">
<div className="flex items-start gap-3">
<div className="h-8 w-8 rounded-lg bg-accent/10 flex items-center justify-center shrink-0 mt-0.5">
<Upload className="h-4 w-4 text-accent" />
</div>
<div>
<div className="text-sm font-medium">Upload a clip</div>
<div className="text-xs text-muted-foreground">
Drag and drop any audio file WAV, MP3, FLAC, or WebM.
</div>
</div>
</div>
<div className="flex items-start gap-3">
<div className="h-8 w-8 rounded-lg bg-accent/10 flex items-center justify-center shrink-0 mt-0.5">
<Mic className="h-4 w-4 text-accent" />
</div>
<div>
<div className="text-sm font-medium">Record from microphone</div>
<div className="text-xs text-muted-foreground">
Live waveform preview while you record. Up to 30 seconds.
</div>
</div>
</div>
<div className="flex items-start gap-3">
<div className="h-8 w-8 rounded-lg bg-accent/10 flex items-center justify-center shrink-0 mt-0.5">
<Monitor className="h-4 w-4 text-accent" />
</div>
<div>
<div className="text-sm font-medium">System audio capture</div>
<div className="text-xs text-muted-foreground">
Clone a voice from a YouTube video, podcast, or any app playing audio.
</div>
</div>
</div>
</div>
</div>
{/* Right: Animated UI mock */}
<div className="rounded-xl border border-app-line bg-app-darkBox overflow-hidden">
<div className="p-5">
{/* Tab bar */}
<div className="flex rounded-lg border border-border bg-card/50 p-1 mb-4">
{TABS.map((tab) => {
const Icon = tab.icon;
const isActive = activeTab === tab.id;
return (
<button
key={tab.id}
onClick={() => {
setActiveTab(tab.id);
setCycleKey((k) => k + 1);
}}
className={`flex-1 flex items-center justify-center gap-1.5 px-3 py-1.5 rounded-md text-xs font-medium transition-colors ${
isActive
? 'bg-background text-foreground shadow-sm'
: 'text-muted-foreground hover:text-foreground'
}`}
>
<Icon className="h-3.5 w-3.5" />
<span className="hidden sm:inline">{tab.label}</span>
</button>
);
})}
</div>
{/* Panel */}
<AnimatePresence mode="wait">
<motion.div
key={`${activeTab}-${cycleKey}`}
initial={{ opacity: 0, y: 6 }}
animate={{ opacity: 1, y: 0 }}
exit={{ opacity: 0, y: -6 }}
transition={{ duration: 0.2 }}
>
{activeTab === 'upload' && <UploadPanel />}
{activeTab === 'record' && <RecordPanel />}
{activeTab === 'system' && <SystemPanel />}
</motion.div>
</AnimatePresence>
</div>
</div>
</div>
</div>
</section>
);
}
+39
View File
@@ -19,6 +19,10 @@ let cachedReleaseInfo: ReleaseInfo | null = null;
let cacheTimestamp: number = 0;
const CACHE_DURATION = 1000 * 60 * 10; // 10 minutes
// Cache for star count
let cachedStarCount: number | null = null;
let starCacheTimestamp: number = 0;
/**
* Fetches the latest release from GitHub and extracts download links
*/
@@ -92,3 +96,38 @@ export async function getLatestRelease(): Promise<ReleaseInfo> {
throw error;
}
}
/**
* Fetches the star count for the repo from GitHub
*/
export async function getStarCount(): Promise<number> {
const now = Date.now();
if (cachedStarCount !== null && now - starCacheTimestamp < CACHE_DURATION) {
return cachedStarCount;
}
try {
const response = await fetch(`${GITHUB_API_BASE}/repos/${GITHUB_REPO}`, {
next: { revalidate: 600 },
headers: {
Accept: 'application/vnd.github.v3+json',
},
});
if (!response.ok) {
throw new Error(`GitHub API error: ${response.status}`);
}
const repo = await response.json();
const count = repo.stargazers_count ?? 0;
cachedStarCount = count;
starCacheTimestamp = now;
return count;
} catch (error) {
console.error('Failed to fetch star count:', error);
if (cachedStarCount !== null) return cachedStarCount;
throw error;
}
}
Binary file not shown.
Binary file not shown.