ci(release): pin free-disk-space action + stop removing LLVM

Review feedback on the Linux release workflow:

1. `jlumbroso/free-disk-space@main` was an unpinned ref in a job that
   runs with `contents: write` and handles signing secrets. Pin to the
   v1.3.1 commit SHA so a force-push or repo compromise can't inject
   arbitrary code into our release flow.

2. `large-packages: true` runs `apt-get remove '^llvm-.*'`, wiping LLVM
   just before the next step installs `llvm-dev`. That wastes CI time
   and risks cascade-removal of reverse deps that won't be pulled back
   in by `llvm-dev` alone. The remaining toggles (android, dotnet,
   haskell, swap-storage) already clear ~20 GB, which is enough
   headroom for the Python + torch + PyInstaller build.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

.github/workflows/release.yml

@@ -26,12 +26,45 @@ jobs:
             args: ""
             python-version: "3.12"
             backend: "pytorch"
+          - platform: "ubuntu-22.04"
+            # --config override disables updater-artifact generation on Linux.
+            # tauri.conf.json has createUpdaterArtifacts: "v1Compatible" which
+            # on Linux wants to synthesize a .AppImage.tar.gz by downloading
+            # linuxdeploy at build time — this is what silently hangs CI
+            # (see v0.4.2 round 2, 25 min of no output after rpm bundling).
+            # We ship deb+rpm only; Linux users update via apt/dnf, not the
+            # Tauri in-app updater.
+            args: '--target x86_64-unknown-linux-gnu --bundles deb,rpm --verbose --config {"bundle":{"createUpdaterArtifacts":false}}'
+            python-version: "3.12"
+            backend: "pytorch"
 
     runs-on: ${{ matrix.platform }}
 
     steps:
       - uses: actions/checkout@v4
 
+      # Ubuntu runners ship with ~14 GB free; pip + PyInstaller + torch can
+      # peak well above that during the build. Reclaim ~25 GB by pruning
+      # preinstalled toolchains we don't use. This is what likely tripped
+      # the March 2026 Linux release attempts (see commit 103e98b
+      # "github runners suck") — not a code issue, a disk-pressure one.
+      - name: Free up disk space (ubuntu)
+        if: contains(matrix.platform, 'ubuntu') || contains(matrix.platform, 'namespace')
+        # Pinned to v1.3.1 (SHA) — this job runs with contents: write and
+        # handles signing secrets later, so we don't want a floating ref.
+        uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be
+        with:
+          tool-cache: false
+          android: true
+          dotnet: true
+          haskell: true
+          # large-packages: true would `apt-get remove '^llvm-.*'`, which
+          # cascade-removes reverse deps that won't be pulled back in by the
+          # `llvm-dev` install below. The other flags already free ~20 GB,
+          # enough for the Python + torch + PyInstaller build.
+          large-packages: false
+          swap-storage: true
+
       - name: Install dependencies (ubuntu only)
         if: contains(matrix.platform, 'ubuntu') || contains(matrix.platform, 'namespace')
         run: |
@@ -133,6 +166,21 @@ jobs:
           p12-file-base64: ${{ secrets.APPLE_CERTIFICATE }}
           p12-password: ${{ secrets.APPLE_CERTIFICATE_PASSWORD }}
 
+      - name: Disk / environment snapshot (pre-bundle debug)
+        if: contains(matrix.platform, 'ubuntu') || contains(matrix.platform, 'namespace')
+        run: |
+          echo "=== df -h ==="
+          df -h
+          echo "=== free -h ==="
+          free -h
+          echo "=== Rust / Cargo ==="
+          rustc --version
+          cargo --version
+          echo "=== Bun ==="
+          bun --version
+          echo "=== Tauri CLI ==="
+          cd tauri && bun run tauri --version
+
       - name: Extract release notes from CHANGELOG.md
         id: changelog
         shell: bash
@@ -156,7 +204,13 @@ jobs:
             echo "CHANGELOG_EOF"
           } >> "$GITHUB_OUTPUT"
 
+      # Linux hang watchdog: previous releases silently wedged inside tauri
+      # bundling (possibly linuxdeploy/AppImage download, possibly cargo link).
+      # Cap the step at 30 min so we get logs instead of waiting out the 6hr
+      # job timeout. Other platforms historically complete in ~25 min, so 45
+      # is comfortable.
       - uses: tauri-apps/[email protected]
+        timeout-minutes: ${{ (contains(matrix.platform, 'ubuntu') || contains(matrix.platform, 'namespace')) && 30 || 45 }}
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           TAURI_SIGNING_PRIVATE_KEY: ${{ secrets.TAURI_SIGNING_PRIVATE_KEY }}
@@ -168,6 +222,9 @@ jobs:
           APPLE_PROVIDER_SHORT_NAME: ${{ secrets.APPLE_PROVIDER_SHORT_NAME }}
           APPLE_API_ISSUER: ${{ secrets.APPLE_API_ISSUER }}
           APPLE_API_KEY: ${{ secrets.APPLE_API_KEY }}
+          # Stream subprocess stdout/stderr so the hang is visible in logs.
+          CARGO_TERM_VERBOSE: "true"
+          RUST_BACKTRACE: "1"
         with:
           projectPath: tauri
           tagName: v__VERSION__

README.md

@@ -62,13 +62,14 @@
 
 ## What is Voicebox?
 
-Voicebox is a **local-first voice cloning studio** — a free and open-source alternative to ElevenLabs. Clone voices from a few seconds of audio, generate speech in 23 languages across 5 TTS engines, apply post-processing effects, and compose multi-voice projects with a timeline editor.
+Voicebox is a **local-first voice cloning studio** — a free and open-source alternative to ElevenLabs. Clone voices from a few seconds of audio or pick from 50+ preset voices, generate speech in 23 languages across 7 TTS engines, apply post-processing effects, and compose multi-voice projects with a timeline editor.
 
 - **Complete privacy** — models and voice data stay on your machine
-- **5 TTS engines** — Qwen3-TTS, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, and HumeAI TADA
+- **7 TTS engines** — Qwen3-TTS, Qwen CustomVoice, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, HumeAI TADA, and Kokoro
+- **Cloning and preset voices** — zero-shot cloning from a reference sample, or curated preset voices via Kokoro (50 voices) and Qwen CustomVoice (9 voices)
 - **23 languages** — from English to Arabic, Japanese, Hindi, Swahili, and more
 - **Post-processing effects** — pitch shift, reverb, delay, chorus, compression, and filters
-- **Expressive speech** — paralinguistic tags like `[laugh]`, `[sigh]`, `[gasp]` via Chatterbox Turbo
+- **Expressive speech** — paralinguistic tags like `[laugh]`, `[sigh]`, `[gasp]` via Chatterbox Turbo; natural-language delivery control via Qwen CustomVoice
 - **Unlimited length** — auto-chunking with crossfade for scripts, articles, and chapters
 - **Stories editor** — multi-track timeline for conversations, podcasts, and narratives
 - **API-first** — REST API for integrating voice synthesis into your own projects
@@ -96,15 +97,17 @@ Voicebox is a **local-first voice cloning studio** — a free and open-source al
 
 ### Multi-Engine Voice Cloning
 
-Five TTS engines with different strengths, switchable per-generation:
+Seven TTS engines with different strengths, switchable per-generation:
 
 | Engine                      | Languages | Strengths                                                                                                                                |
 | --------------------------- | --------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
 | **Qwen3-TTS** (0.6B / 1.7B) | 10        | High-quality multilingual cloning, delivery instructions ("speak slowly", "whisper")                                                     |
+| **Qwen CustomVoice**        | 10        | 9 curated preset voices with natural-language delivery control — no reference audio required                                             |
 | **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                                                                                   |
 | **TADA** (1B / 3B)          | 10        | HumeAI speech-language model — 700s+ coherent audio, text-acoustic dual alignment                                                        |
+| **Kokoro**                  | 8         | 50 curated preset voices, tiny 82M model, fast CPU inference                                                                             |
 
 ### Emotions & Paralinguistic Tags
 
@@ -239,7 +242,7 @@ Full API documentation available at `http://localhost:17493/docs`.
 | Frontend      | React, TypeScript, Tailwind CSS                   |
 | State         | Zustand, React Query                              |
 | Backend       | FastAPI (Python)                                  |
-| TTS Engines   | Qwen3-TTS, LuxTTS, Chatterbox, Chatterbox Turbo, TADA |
+| TTS Engines   | Qwen3-TTS, Qwen CustomVoice, LuxTTS, Chatterbox, Chatterbox Turbo, TADA, Kokoro |
 | Effects       | Pedalboard (Spotify)                              |
 | Transcription | Whisper / Whisper Turbo (PyTorch or MLX)          |
 | Inference     | MLX (Apple Silicon) / PyTorch (CUDA/ROCm/XPU/CPU) |

app/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@voicebox/app",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "private": true,
   "type": "module",
   "scripts": {

app/src/components/AppFrame/AppFrame.tsx

@@ -1,5 +1,6 @@
 import { useRouterState } from '@tanstack/react-router';
 import { TitleBarDragRegion } from '@/components/TitleBarDragRegion';
+import { AudioKeepAlive } from '@/components/AudioPlayer/AudioKeepAlive';
 import { AudioPlayer } from '@/components/AudioPlayer/AudioPlayer';
 import { StoryTrackEditor } from '@/components/StoriesTab/StoryTrackEditor';
 import { TOP_SAFE_AREA_PADDING } from '@/lib/constants/ui';
@@ -26,6 +27,7 @@ export function AppFrame({ children }: AppFrameProps) {
       className={cn('h-screen bg-background flex flex-col overflow-hidden', TOP_SAFE_AREA_PADDING)}
     >
       <TitleBarDragRegion />
+      <AudioKeepAlive />
       {children}
       {showTrackEditor ? (
         <StoryTrackEditor storyId={story.id} items={story.items} />

app/src/components/AudioPlayer/AudioKeepAlive.tsx

@@ -0,0 +1,85 @@
+import { useEffect, useRef } from 'react';
+import { debug } from '@/lib/utils/debug';
+
+// WKWebView tears down the app's CoreAudio output when idle for long enough,
+// and a JS-level reload (cmd+R) does NOT restore it — only relaunching the
+// Tauri app does. Keeping a silent <audio> element looping forever prevents
+// the OS audio session from ever going dormant.
+//
+// Real silence (zero PCM samples) at full volume is preferred over a muted
+// element: browsers/WebKit can optimize muted media away, which defeats the
+// purpose of holding the session open.
+
+function buildSilentWavUrl(seconds = 1, sampleRate = 8000): string {
+  const numSamples = seconds * sampleRate;
+  const bytes = 44 + numSamples * 2;
+  const buffer = new ArrayBuffer(bytes);
+  const view = new DataView(buffer);
+  const write = (offset: number, str: string) => {
+    for (let i = 0; i < str.length; i++) view.setUint8(offset + i, str.charCodeAt(i));
+  };
+  write(0, 'RIFF');
+  view.setUint32(4, bytes - 8, true);
+  write(8, 'WAVE');
+  write(12, 'fmt ');
+  view.setUint32(16, 16, true);
+  view.setUint16(20, 1, true);
+  view.setUint16(22, 1, true);
+  view.setUint32(24, sampleRate, true);
+  view.setUint32(28, sampleRate * 2, true);
+  view.setUint16(32, 2, true);
+  view.setUint16(34, 16, true);
+  write(36, 'data');
+  view.setUint32(40, numSamples * 2, true);
+  return URL.createObjectURL(new Blob([buffer], { type: 'audio/wav' }));
+}
+
+export function AudioKeepAlive() {
+  const audioRef = useRef<HTMLAudioElement | null>(null);
+
+  useEffect(() => {
+    const url = buildSilentWavUrl(1, 8000);
+    const el = new Audio(url);
+    el.loop = true;
+    el.volume = 1;
+    el.preload = 'auto';
+    audioRef.current = el;
+
+    const tryPlay = () => {
+      if (!audioRef.current) return;
+      if (!audioRef.current.paused) return;
+      audioRef.current.play().catch((err) => {
+        debug.log('[AudioKeepAlive] play blocked (will retry on next gesture):', err);
+      });
+    };
+
+    tryPlay();
+
+    // Autoplay may be blocked until first user interaction — re-attempt then.
+    const onGesture = () => tryPlay();
+    window.addEventListener('pointerdown', onGesture, { once: false });
+    window.addEventListener('keydown', onGesture, { once: false });
+
+    // If the webview ever pauses the element on background, resume on return.
+    const onWake = () => {
+      if (!document.hidden) tryPlay();
+    };
+    document.addEventListener('visibilitychange', onWake);
+    window.addEventListener('focus', onWake);
+    window.addEventListener('pageshow', onWake);
+
+    return () => {
+      window.removeEventListener('pointerdown', onGesture);
+      window.removeEventListener('keydown', onGesture);
+      document.removeEventListener('visibilitychange', onWake);
+      window.removeEventListener('focus', onWake);
+      window.removeEventListener('pageshow', onWake);
+      el.pause();
+      el.src = '';
+      URL.revokeObjectURL(url);
+      audioRef.current = null;
+    };
+  }, []);
+
+  return null;
+}

landing/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@voicebox/landing",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Landing page for voicebox.sh",
   "scripts": {
     "dev": "bun --bun next dev --turbo",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "voicebox",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "private": true,
   "workspaces": [
     "app",

tauri/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@voicebox/tauri",
   "private": true,
-  "version": "0.4.1",
+  "version": "0.4.2",
   "type": "module",
   "scripts": {
     "dev": "vite",

tauri/src-tauri/Cargo.lock

@@ -5041,7 +5041,7 @@ checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
 [[package]]
 name = "voicebox"
-version = "0.4.0"
+version = "0.4.2"
 dependencies = [
  "base64 0.22.1",
  "core-foundation-sys",

tauri/src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "voicebox"
-version = "0.4.1"
+version = "0.4.2"
 description = "A production-quality desktop app for Qwen3-TTS voice cloning and generation"
 authors = ["you"]
 license = ""

tauri/src-tauri/tauri.conf.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://schema.tauri.app/config/2",
   "productName": "Voicebox",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "identifier": "sh.voicebox.app",
   "build": {
     "beforeDevCommand": "bun run dev",

web/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@voicebox/web",
   "private": true,
-  "version": "0.4.1",
+  "version": "0.4.2",
   "type": "module",
   "scripts": {
     "dev": "vite",