`omnivoice-clone`

OmniVoice clone. Same knobs as speech, plus optional instruct.

Native waveform: 24 kHz mono. Live price and availability are on GET /v1/models/omnivoice-clone.

reference_text is required.

Parameters

Field	Type	Description
`params.language` Default Auto	string	OmniVoice only. Display name or Auto. Default Auto.
`params.num_step` Default 32	integer	OmniVoice only. 4 to 64. Default 32. More is usually cleaner and slower.
`params.guidance_scale` Default 2	number	OmniVoice only. 0 to 4. Default 2. Higher follows the text more tightly.
`params.speed` Default 1	number	OmniVoice only. 0.5 to 1.5. Default 1.
`params.instruct` Default omitted	string	OmniVoice clone only. Optional style. Design uses voice_description instead.
`params.denoise` Default true	boolean	OmniVoice only. Default true.
`params.postprocess_output` Default true	boolean	OmniVoice only. Default true.
`params.preprocess_prompt` Default true	boolean	OmniVoice clone only. Clean the reference clip first. 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=omnivoice-clone \
  -F text="Keep walking toward the river." \
  -F reference_text="Hello, my name is Ada." \
  -F params='{"language":"Auto","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"