GET /v1/voices GET¶
GEThttps://api.vartalaap.si/v1/voices
tts.sh
curl -s https://api.vartalaap.si/v1/voices -H "x-api-key: $VARTALAAP_API_KEY"
js title="tts.mjs"on
{
"voices": [
{"name": "saanvi", "language": "hi-IN+en-IN", "gender": "female", "style": "", "styles": ["excited", "sad", "whisper"], "sample_rate": 24000, "prompt_frames": 102, "model": "pocket-tts-hinglish-v2.0-sft3000"},
{"name": "sahil", "language": "hi-IN+en-IN", "gender": "male", "style": "", "styles": ["excited", "sad", "whisper"], "sample_rate": 24000, "prompt_frames": 102, "model": "pocket-tts-hinglish-v2.0-sft3000"},
{"name": "meera", "language": "hi-IN+en-IN", "gender": "female", "style": "", "styles": [], "sample_rate": 24000, "prompt_frames": 102, "model": "pocket-tts-hinglish-v2.0-sft3000"},
… the other 18 Hinglish voices …,
{"name": "kiara", "language": "en", "gender": "female", "style": "reading", "styles": [], "sample_rate": 24000, "prompt_frames": 146, "model": "pocket-tts-english-v1"},
{"name": "kevin", "language": "en", "gender": "male", "style": "reading", "styles": [], "sample_rate": 24000, "prompt_frames": 125, "model": "pocket-tts-english-v1"},
… the other 16 English (US) voices …
],
"model": "pocket-tts-hinglish-v2.0-sft3000",
"language": "hi-IN+en-IN"
}
| Field | |
|---|---|
language |
hi-IN+en-IN for Hinglish voices, en for English (US) voices. Decides which normaliser the text goes through. |
gender |
female / male |
style |
English (US) voices: reading (steady, narrated) or conversation (phrased like speech). Empty for Hinglish. |
styles |
the expressions the voice accepts in the request field style: ["excited", "sad", "whisper"] for saanvi and sahil, [] for every other voice. Expressions are not listed as voices of their own. |
model |
the model that serves the voice; model at the top level is the Hinglish one. |
Only the voices the presented key may use are listed (see voice allow-lists). prompt_frames
is the length of the voice prompt the model was conditioned on, for the curious. Requires a key (401 otherwise).