feat: add Qwen CustomVoice preset engine

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
+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;
+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. */
+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,