GET

/v1/schemas/fish-audio/audio/v1/voice-design?kind=output

kind outputactivity audiohash 9009cc2d…extracted Nov 10, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
698642cc0dd247e854fa9711b7d1d26916770ad466e2ae77dc9d983379dc5647
{
  "fetchedAt": 1794288623,
  "extractorVersion": "2",
  "verifiedAt": null
}

Response body

1 properties · 1 required · 1 $defs
propertytypedescriptionconstraints
candidates*VoiceDesignCandidate[]Generated voice candidates.

Types

1 $defs

VoiceDesignCandidateobject

id*stringStable candidate identifier.
index*integerCandidate index in this response.n ≥ 0
audio_base64*stringBase64 encoded generated audio.
sample_rate*integerAudio sample rate in Hz.n > 0
duration_ms*integerAudio duration in milliseconds.n ≥ 0
textstringPreview text associated with this generated voice, when available.nullable
instructstringInstruction text associated with this candidate, when available.nullable
languagestringDetected or requested candidate language, when available.nullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fish-audio","endpointId":"v1/voice-design","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}