`auk-flash-voice-design`

Describe a voice, then speak text. No reference clip. Send model auk-flash-voice-design.

Native waveform: 24 kHz mono. Live price and availability are on GET /v1/models/auk-flash-voice-design.

voice_description is free-form English.
NFE and CFG are not request fields.

Parameters

Field	Type	Description
`params.seed` Default 0	integer	AuK only. 0 produces a new output on every run and cannot be reproduced. A positive integer locks an output. NFE and CFG are not request fields.
`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-design \
  -H "Authorization: Bearer $PASCAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "auk-flash-voice-design",
  "text": "Keep walking toward the river.",
  "voice_description": "A calm adult narrator with a warm, clear, neutral voice.",
  "params": {
    "seed": 7,
    "output_format": "wav"
  }
}'

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