omnivoice-voice-design
OmniVoice. voice_description is tags only.
Native waveform: 24 kHz mono. Live price and availability are on GET /v1/models/omnivoice-voice-design.
- voice_description is a comma-separated list of tags.
- English tags: american accent, australian accent, british accent, canadian accent, child, chinese accent, elderly, female, high pitch, indian accent, japanese accent, korean accent, low pitch, male, middle-aged, moderate pitch, portuguese accent, russian accent, teenager, very high pitch, very low pitch, whisper, young adult.
- Chinese dialect and age tags are also accepted.
Parameters
| Field | Type | Description |
|---|---|---|
params.languageDefault Auto | string | OmniVoice only. Display name or Auto. Default Auto. |
params.num_stepDefault 32 | integer | OmniVoice only. 4 to 64. Default 32. More is usually cleaner and slower. |
params.guidance_scaleDefault 2 | number | OmniVoice only. 0 to 4. Default 2. Higher follows the text more tightly. |
params.speedDefault 1 | number | OmniVoice only. 0.5 to 1.5. Default 1. |
params.denoiseDefault true | boolean | OmniVoice only. Default true. |
params.postprocess_outputDefault true | boolean | OmniVoice only. Default true. |
params.output_formatDefault wav (flac for stems) | string | wav, flac, mp3, or model (the model native file). |
params.output_sample_rateDefault 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_channelsDefault source | string | source, model, mono, or stereo. Applied after inference, not before. |
Example
curl https://api.pascalai.co/v1/voice-design \
-H "Authorization: Bearer $PASCAL_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "omnivoice-voice-design",
"text": "Keep walking toward the river.",
"voice_description": "female, low pitch",
"params": {
"language": "Auto",
"output_format": "wav"
}
}'
curl https://api.pascalai.co/v1/voice-design/$JOB_ID \
-H "Authorization: Bearer $PASCAL_API_KEY"