Fish Audio · Speech Audio

FishAudio OpenAPI / Voice Design

Design new voices from a written prompt with Fish Audio voice design. Returns 1 to 4 candidate voices with a sample audio file each. Flat price per request, whatever the number of candidates.

Live data

You are looking at the live public catalog.

unverifiedRequest shape unavailableUnverified

Published API evidence

Public metadata only. Response bodies, credentials, and internal review notes are never displayed.

No verification date is claimed. No response capture is claimed.

Request parameters

guidance_scale body · optional
Classifier-free guidance scale. Higher values follow the prompt more strongly.
instruct_guidance_scale body · optional
Instruction guidance scale for prompt conditioning.
instruction body · required
Voice design prompt. Must contain 1 to 2000 characters.
language body · optional
n body · optional
Number of voice candidates, 1 to 4.
num_step body · optional
Number of diffusion steps used by the voice-design model.
reference_text body · optional
seed body · optional
speed body · optional
Speaking speed multiplier for candidate generation.
model header · optional

No allowlisted official documentation or pricing reference is available.