danvics/openreader
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat(replicate): add support for custom Replicate model selection

Browse source
This commit is contained in:
Richard R 2026-04-16 11:24:19 -06:00
parent 9da9232d39
commit d0c0ab7420
3 changed files with 16 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
docs-site/docs/configure/tts-provider-guides/replicate.md
View file

@ -29,6 +29,7 @@ Settings modal values override env vars. See [TTS Providers](../tts-providers) f
- `minimax/speech-2.8-turbo` - `minimax/speech-2.8-turbo`
- `qwen/qwen3-tts` - `qwen/qwen3-tts`
- `inworld/tts-1.5-mini` - `inworld/tts-1.5-mini`
- You can also choose `Other` and enter any Replicate model ID (for example `owner/model-name`).
- Native model speed is not available on all Replicate models; OpenReader hides/disables native speed controls where unsupported. - Native model speed is not available on all Replicate models; OpenReader hides/disables native speed controls where unsupported.
- TTS requests are sent from the server, not the browser. The API key is never exposed to clients. - TTS requests are sent from the server, not the browser. The API key is never exposed to clients.

2
docs-site/docs/configure/tts-providers.md
View file

@ -23,7 +23,7 @@ For `OpenAI`, `Deepinfra`, and `Replicate` you only need to supply an API key. F
## Built-in model catalogs ## Built-in model catalogs
- **Replicate** models: `google/gemini-3.1-flash-tts`, `minimax/speech-2.8-turbo`, `qwen/qwen3-tts`, `inworld/tts-1.5-mini` - **Replicate** models: `google/gemini-3.1-flash-tts`, `minimax/speech-2.8-turbo`, `qwen/qwen3-tts`, `inworld/tts-1.5-mini` (or choose `Other` and enter any Replicate model ID)
- **OpenAI** models: `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts` - **OpenAI** models: `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`
- **Deepinfra** models: includes `hexgrad/Kokoro-82M` and additional hosted models (depending on API key / feature flags) - **Deepinfra** models: includes `hexgrad/Kokoro-82M` and additional hosted models (depending on API key / feature flags)

18
src/lib/shared/tts-provider-catalog.ts
View file

@ -59,6 +59,7 @@ const REPLICATE_MODELS: TtsModelDefinition[] = [
{ id: 'minimax/speech-2.8-turbo', name: 'MiniMax Speech 2.8 Turbo' }, { id: 'minimax/speech-2.8-turbo', name: 'MiniMax Speech 2.8 Turbo' },
{ id: 'qwen/qwen3-tts', name: 'Qwen3 TTS' }, { id: 'qwen/qwen3-tts', name: 'Qwen3 TTS' },
{ id: 'inworld/tts-1.5-mini', name: 'Inworld TTS 1.5 Mini' }, { id: 'inworld/tts-1.5-mini', name: 'Inworld TTS 1.5 Mini' },
{ id: 'custom', name: 'Other' },
]; ];
const DEFAULT_MODELS: TtsModelDefinition[] = [{ id: 'tts-1', name: 'TTS-1' }]; const DEFAULT_MODELS: TtsModelDefinition[] = [{ id: 'tts-1', name: 'TTS-1' }];
@ -104,7 +105,7 @@ export const TTS_PROVIDER_DEFINITIONS: TtsProviderDefinition[] = [
{ {
id: 'replicate', id: 'replicate',
name: 'Replicate', name: 'Replicate',
supportsCustomModel: false, supportsCustomModel: true,
models: () => REPLICATE_MODELS, models: () => REPLICATE_MODELS,
}, },
{ {
@ -137,6 +138,11 @@ const REPLICATE_MODELS_WITHOUT_NATIVE_SPEED = new Set([
'qwen/qwen3-tts', 'qwen/qwen3-tts',
]); ]);
const REPLICATE_MODELS_WITH_NATIVE_SPEED = new Set([
'minimax/speech-2.8-turbo',
'inworld/tts-1.5-mini',
]);
export function supportsTtsInstructions(model: string | null | undefined): boolean { export function supportsTtsInstructions(model: string | null | undefined): boolean {
return !!model && MODELS_WITH_INSTRUCTIONS.has(model); return !!model && MODELS_WITH_INSTRUCTIONS.has(model);
} }
@ -146,8 +152,12 @@ export function supportsNativeModelSpeed(provider: string | null | undefined, mo
return true; return true;
} }
if (provider === 'replicate' && REPLICATE_MODELS_WITHOUT_NATIVE_SPEED.has(model)) { if (provider === 'replicate') {
return false; if (REPLICATE_MODELS_WITHOUT_NATIVE_SPEED.has(model)) {
return false;
}
return REPLICATE_MODELS_WITH_NATIVE_SPEED.has(model);
} }
return true; return true;
@ -193,7 +203,7 @@ export function getDefaultVoices(provider: string, model: string): string[] {
if (model === 'inworld/tts-1.5-mini') { if (model === 'inworld/tts-1.5-mini') {
return [...INWORLD_TTS_VOICES]; return [...INWORLD_TTS_VOICES];
} }
return [...GEMINI_FLASH_TTS_VOICES]; return ['default'];
} }
if (provider === 'deepinfra') { if (provider === 'deepinfra') {