Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-09-17 13:50:39 -07:00
Code Issues Packages Projects Releases Wiki Activity

feat: add Qwen CustomVoice preset engine

Browse Source
This commit is contained in:
James Pine
2026-03-19 19:48:50 -07:00
parent d70b878b71
commit 4e0c731db8
14 changed files with 399 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/src/components/Generation/EngineModelSelector.tsx
+14 -1
View File
@@ -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');
app/src/components/Generation/GenerationForm.tsx
+1 -1
View File
@@ -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"
app/src/components/ServerSettings/ModelManagement.tsx
+5
View File
@@ -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') ||
app/src/components/VoiceProfiles/ProfileCard.tsx
+7 -1
View File
@@ -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' && (
app/src/components/VoiceProfiles/ProfileForm.tsx
+3 -1
View File
@@ -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>
app/src/components/VoiceProfiles/ProfileList.tsx
+2 -1
View File
@@ -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() {
app/src/lib/api/types.ts
+8 -1
View File
@@ -62,7 +62,14 @@ export interface GenerationRequest {
language: LanguageCode;
seed?: number;
model_size?: '1.7B' | '0.6B' | '1B' | '3B';
engine?: 'qwen' | 'luxtts' | 'chatterbox' | 'chatterbox_turbo' | 'tada' | 'kokoro';
engine?:
| 'qwen'
| 'qwen_custom_voice'
| 'luxtts'
| 'chatterbox'
| 'chatterbox_turbo'
| 'tada'
| 'kokoro';
instruct?: string;
max_chunk_chars?: number;
crossfade_ms?: number;
app/src/lib/constants/languages.ts
+1
View File
@@ -69,6 +69,7 @@ export const ENGINE_LANGUAGES: Record<string, readonly LanguageCode[]> = {
chatterbox_turbo: ['en'],
tada: ['en', 'ar', 'zh', 'de', 'es', 'fr', 'it', 'ja', 'pl', 'pt'],
kokoro: ['en', 'es', 'fr', 'hi', 'it', 'pt', 'ja', 'zh'],
qwen_custom_voice: ['zh', 'en', 'ja', 'ko', 'de', 'fr', 'ru', 'pt', 'es', 'it'],
} as const;
/** Helper: get language options for a given engine. */
app/src/lib/hooks/useGenerationForm.ts
+25 -7
View File
@@ -17,7 +17,17 @@ const generationSchema = z.object({
seed: z.number().int().optional(),
modelSize: z.enum(['1.7B', '0.6B', '1B', '3B']).optional(),
instruct: z.string().max(500).optional(),
engine: z.enum(['qwen', 'luxtts', 'chatterbox', 'chatterbox_turbo', 'tada', 'kokoro']).optional(),
engine: z
.enum([
'qwen',
'qwen_custom_voice',
'luxtts',
'chatterbox',
'chatterbox_turbo',
'tada',
'kokoro',
])
.optional(),
});
export type GenerationFormValues = z.infer<typeof generationSchema>;
@@ -85,7 +95,9 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
: 'tada-1b'
: engine === 'kokoro'
? 'kokoro'
: `qwen-tts-${data.modelSize}`;
: engine === 'qwen_custom_voice'
? `qwen-custom-voice-${data.modelSize}`
: `qwen-tts-${data.modelSize}`;
const displayName =
engine === 'luxtts'
? 'LuxTTS'
@@ -99,9 +111,13 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
: 'TADA 1B'
: engine === 'kokoro'
? 'Kokoro 82M'
: data.modelSize === '1.7B'
? 'Qwen TTS 1.7B'
: 'Qwen TTS 0.6B';
: engine === 'qwen_custom_voice'
? data.modelSize === '1.7B'
? 'Qwen CustomVoice 1.7B'
: 'Qwen CustomVoice 0.6B'
: data.modelSize === '1.7B'
? 'Qwen TTS 1.7B'
: 'Qwen TTS 0.6B';
// Check if model needs downloading
try {
@@ -116,7 +132,9 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
console.error('Failed to check model status:', error);
}
const hasModelSizes = engine === 'qwen' || engine === 'tada';
const hasModelSizes =
engine === 'qwen' || engine === 'qwen_custom_voice' || engine === 'tada';
const supportsInstruct = engine === 'qwen' || engine === 'qwen_custom_voice';
const effectsChain = options.getEffectsChain?.();
// This now returns immediately with status="generating"
const result = await generation.mutateAsync({
@@ -126,7 +144,7 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
seed: data.seed,
model_size: hasModelSizes ? data.modelSize : undefined,
engine,
instruct: engine === 'qwen' ? data.instruct || undefined : undefined,
instruct: supportsInstruct ? data.instruct || undefined : undefined,
max_chunk_chars: maxChunkChars,
crossfade_ms: crossfadeMs,
normalize: normalizeAudio,