`kokoro`

Text to speech. Voices across nine languages, plus speed.

Native waveform: 24 kHz mono int16 WAV. Live price and availability are on GET /v1/models/kokoro.

Parameters

Field	Type	Description
`params.voice` Default af_heart	string	Kokoro only. 54 speakers across US, UK, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Mandarin. First letter is the language. Rejected on every other speech model.
`params.speed` Default 1	number	Kokoro only. 0.5 to 2. Default 1. Rejected on every other speech model.
`params.output_format` Default wav (flac for stems)	string	wav, flac, mp3, or model (the model native file).
`params.output_sample_rate` Default source	string or integer	source keeps the upload (or the model rate when there is no upload). model uses the model native rate. Or pass 8000, 16000, 22050, 24000, 32000, 44100, or 48000.
`params.output_channels` Default source	string	source, model, mono, or stereo. Applied after inference, not before.

Example

curl https://api.pascalai.co/v1/text-to-speech \
  -H "Authorization: Bearer $PASCAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "kokoro",
  "text": "Keep walking toward the river.",
  "params": {
    "voice": "af_heart",
    "speed": 1,
    "output_format": "wav",
    "output_sample_rate": "source",
    "output_channels": "source"
  }
}'

curl https://api.pascalai.co/v1/text-to-speech/$JOB_ID \
  -H "Authorization: Bearer $PASCAL_API_KEY"