mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 21:30:39 -07:00
feat: add Qwen CustomVoice preset engine
This commit is contained in:
@@ -19,6 +19,8 @@ import type { GenerationFormValues } from '@/lib/hooks/useGenerationForm';
|
||||
const ENGINE_OPTIONS = [
|
||||
{ value: 'qwen:1.7B', label: 'Qwen3-TTS 1.7B', engine: 'qwen' },
|
||||
{ value: 'qwen:0.6B', label: 'Qwen3-TTS 0.6B', engine: 'qwen' },
|
||||
{ value: 'qwen_custom_voice:1.7B', label: 'Qwen CustomVoice 1.7B', engine: 'qwen_custom_voice' },
|
||||
{ value: 'qwen_custom_voice:0.6B', label: 'Qwen CustomVoice 0.6B', engine: 'qwen_custom_voice' },
|
||||
{ value: 'luxtts', label: 'LuxTTS', engine: 'luxtts' },
|
||||
{ value: 'chatterbox', label: 'Chatterbox', engine: 'chatterbox' },
|
||||
{ value: 'chatterbox_turbo', label: 'Chatterbox Turbo', engine: 'chatterbox_turbo' },
|
||||
@@ -29,6 +31,7 @@ const ENGINE_OPTIONS = [
|
||||
|
||||
const ENGINE_DESCRIPTIONS: Record<string, string> = {
|
||||
qwen: 'Multi-language, two sizes',
|
||||
qwen_custom_voice: '9 preset voices, instruct control',
|
||||
luxtts: 'Fast, English-focused',
|
||||
chatterbox: '23 languages, incl. Hebrew',
|
||||
chatterbox_turbo: 'English, [laugh] [cough] tags',
|
||||
@@ -49,12 +52,22 @@ function getAvailableOptions(selectedProfile?: VoiceProfileResponse | null) {
|
||||
|
||||
function getSelectValue(engine: string, modelSize?: string): string {
|
||||
if (engine === 'qwen') return `qwen:${modelSize || '1.7B'}`;
|
||||
if (engine === 'qwen_custom_voice') return `qwen_custom_voice:${modelSize || '1.7B'}`;
|
||||
if (engine === 'tada') return `tada:${modelSize || '1B'}`;
|
||||
return engine;
|
||||
}
|
||||
|
||||
function handleEngineChange(form: UseFormReturn<GenerationFormValues>, value: string) {
|
||||
if (value.startsWith('qwen:')) {
|
||||
if (value.startsWith('qwen_custom_voice:')) {
|
||||
const [, modelSize] = value.split(':');
|
||||
form.setValue('engine', 'qwen_custom_voice');
|
||||
form.setValue('modelSize', modelSize as '1.7B' | '0.6B');
|
||||
const currentLang = form.getValues('language');
|
||||
const available = getLanguageOptionsForEngine('qwen_custom_voice');
|
||||
if (!available.some((l) => l.value === currentLang)) {
|
||||
form.setValue('language', available[0]?.value ?? 'en');
|
||||
}
|
||||
} else if (value.startsWith('qwen:')) {
|
||||
const [, modelSize] = value.split(':');
|
||||
form.setValue('engine', 'qwen');
|
||||
form.setValue('modelSize', modelSize as '1.7B' | '0.6B');
|
||||
|
||||
@@ -91,7 +91,7 @@ export function GenerationForm() {
|
||||
)}
|
||||
/>
|
||||
|
||||
{form.watch('engine') === 'qwen' && (
|
||||
{(form.watch('engine') === 'qwen' || form.watch('engine') === 'qwen_custom_voice') && (
|
||||
<FormField
|
||||
control={form.control}
|
||||
name="instruct"
|
||||
|
||||
@@ -68,6 +68,10 @@ const MODEL_DESCRIPTIONS: Record<string, string> = {
|
||||
'HumeAI TADA 3B Multilingual — built on Llama 3.2 3B. Supports 10 languages with high-fidelity voice cloning via text-acoustic dual alignment.',
|
||||
kokoro:
|
||||
'Kokoro 82M by hexgrad. Tiny 82M-parameter TTS that runs at CPU realtime. Supports 8 languages with pre-built voice styles. Apache 2.0 licensed.',
|
||||
'qwen-custom-voice-1.7B':
|
||||
'Qwen3-TTS CustomVoice 1.7B by Alibaba. 9 premium preset voices with instruct-based style control for tone, emotion, and prosody. Supports 10 languages.',
|
||||
'qwen-custom-voice-0.6B':
|
||||
'Qwen3-TTS CustomVoice 0.6B by Alibaba. Lightweight version with the same 9 preset voices and instruct control. Faster inference for lower-end hardware.',
|
||||
'whisper-base':
|
||||
'Smallest Whisper model (74M parameters). Fast transcription with moderate accuracy.',
|
||||
'whisper-small':
|
||||
@@ -396,6 +400,7 @@ export function ModelManagement() {
|
||||
modelStatus?.models.filter(
|
||||
(m) =>
|
||||
m.model_name.startsWith('qwen-tts') ||
|
||||
m.model_name.startsWith('qwen-custom-voice') ||
|
||||
m.model_name.startsWith('luxtts') ||
|
||||
m.model_name.startsWith('chatterbox') ||
|
||||
m.model_name.startsWith('tada') ||
|
||||
|
||||
@@ -17,6 +17,12 @@ import { useDeleteProfile, useExportProfile } from '@/lib/hooks/useProfiles';
|
||||
import { cn } from '@/lib/utils/cn';
|
||||
import { useUIStore } from '@/stores/uiStore';
|
||||
|
||||
/** Human-readable display names for preset engine badges. */
|
||||
const ENGINE_DISPLAY_NAMES: Record<string, string> = {
|
||||
kokoro: 'Kokoro',
|
||||
qwen_custom_voice: 'CustomVoice',
|
||||
};
|
||||
|
||||
interface ProfileCardProps {
|
||||
profile: VoiceProfileResponse;
|
||||
}
|
||||
@@ -99,7 +105,7 @@ export function ProfileCard({ profile }: ProfileCardProps) {
|
||||
</Badge>
|
||||
{profile.voice_type === 'preset' && (
|
||||
<Badge variant="secondary" className="text-xs h-5 px-1.5">
|
||||
{profile.preset_engine}
|
||||
{ENGINE_DISPLAY_NAMES[profile.preset_engine ?? ''] ?? profile.preset_engine}
|
||||
</Badge>
|
||||
)}
|
||||
{profile.voice_type === 'designed' && (
|
||||
|
||||
@@ -60,9 +60,10 @@ import { AudioSampleUpload } from './AudioSampleUpload';
|
||||
import { SampleList } from './SampleList';
|
||||
|
||||
const MAX_AUDIO_DURATION_SECONDS = 30;
|
||||
const PRESET_ONLY_ENGINES = new Set(['kokoro']);
|
||||
const PRESET_ONLY_ENGINES = new Set(['kokoro', 'qwen_custom_voice']);
|
||||
const DEFAULT_ENGINE_OPTIONS = [
|
||||
{ value: 'qwen', label: 'Qwen3-TTS' },
|
||||
{ value: 'qwen_custom_voice', label: 'Qwen CustomVoice' },
|
||||
{ value: 'luxtts', label: 'LuxTTS' },
|
||||
{ value: 'chatterbox', label: 'Chatterbox' },
|
||||
{ value: 'chatterbox_turbo', label: 'Chatterbox Turbo' },
|
||||
@@ -849,6 +850,7 @@ export function ProfileForm() {
|
||||
</FormControl>
|
||||
<SelectContent>
|
||||
<SelectItem value="kokoro">Kokoro 82M</SelectItem>
|
||||
<SelectItem value="qwen_custom_voice">Qwen CustomVoice</SelectItem>
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</FormItem>
|
||||
|
||||
@@ -7,11 +7,12 @@ import { ProfileCard } from './ProfileCard';
|
||||
import { ProfileForm } from './ProfileForm';
|
||||
|
||||
/** Engines that use preset (built-in) voices instead of cloned profiles. */
|
||||
const PRESET_ENGINES = new Set(['kokoro']);
|
||||
const PRESET_ENGINES = new Set(['kokoro', 'qwen_custom_voice']);
|
||||
|
||||
/** Human-readable engine names for empty state messages. */
|
||||
const ENGINE_NAMES: Record<string, string> = {
|
||||
kokoro: 'Kokoro',
|
||||
qwen_custom_voice: 'Qwen CustomVoice',
|
||||
};
|
||||
|
||||
export function ProfileList() {
|
||||
|
||||
Reference in New Issue
Block a user