`chatterbox-turbo-clone`

Chatterbox Turbo zero-shot clone.

Native waveform: 24 kHz mono. Reference must be longer than 5 seconds.. Live price and availability are on GET /v1/models/chatterbox-turbo-clone.

reference_text is ignored.
A reference shorter than 5 seconds is rejected.
Same Turbo tags as speech. exaggeration and cfg_weight are rejected.

Parameters

Field	Type	Description
`params.temperature` Default 0.8	number	Turbo only. 0.05 to 2. Default 0.8. Same on speech and clone.
`params.top_p` Default 0.95	number	Turbo only. 0 to 1. Default 0.95.
`params.top_k` Default 1000	integer	Turbo only. 0 to 1000. Default 1000.
`params.repetition_penalty` Default 1.2	number	Turbo only. 1 to 2. Default 1.2.
`params.seed` Default 0	integer	0 is a new take each run. Same on speech and clone.
`params.norm_loudness` Default true	boolean	Turbo clone only. Loudness match at -27 LUFS. Default true.
`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/voice-cloning \
  -H "Authorization: Bearer $PASCAL_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -F model=chatterbox-turbo-clone \
  -F text="Keep walking toward the river." \
  -F params='{"output_format":"wav","output_sample_rate":"source","output_channels":"source"}' \
  -F file=@voice.wav

curl https://api.pascalai.co/v1/voice-cloning/$JOB_ID \
  -H "Authorization: Bearer $PASCAL_API_KEY"