GET
/v1/schemas/fish-audio/audio/model
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace698642cc0dd247e854fa9711b7d1d26916770ad466e2ae77dc9d983379dc5647{
"fetchedAt": 1794288623,
"extractorVersion": "2",
"verifiedAt": null
} |
Request body
12 properties · 4 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| type* | const | Model type, tts is for text to speech | "tts" |
| title* | string | Model title or name | |
| train_mode* | const | Model train mode, for TTS model, fast means model instantly available after creation | "fast" |
| voices* | string[] | string | Upload voices files that will be used to tune the model | |
| visibility | enum | Model visibility. Public requests are downgraded to private; use the web publish flow to publish publicly. Unlist allows anyone with the link to access, while private is visible only to the creator. | public | unlist | private · default: "private" |
| description | string | Model description | nullable |
| cover_image | string | Model cover image, this is required if the model is public | format: binary · nullable |
| texts | string[] | string | Texts corresponding to the voices, if unspecified, ASR will be performed on the voices | nullable · default: null |
| voice_design_signatures | string[] | string | Signatures from /v1/voice-design candidates, one per voice in the same order. When every uploaded voice verifies, the model is stamped source=voice_design; an invalid signature rejects the request. | nullable · default: null |
| tags | string[] | string | Model tags | nullable |
| enhance_audio_quality | boolean | Enhance audio quality | default: true |
| generate_sample | boolean | Generate default text | default: false |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fish-audio","endpointId":"model","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}