GET

/v1/schemas/fal/audio/fal-ai/qwen-3-tts/clone-voice/0.6b

kind inputactivity audiohash 34efd898…extracted Oct 9, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
77ee085ae7b4c88447ba92a37b48b01d7b066ec0951c18aa6450ada8eaeef8b5
{
  "fetchedAt": 1791522002,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

3 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
audio_url*stringURL to the reference audio file used for voice cloning. Must be at most 300 seconds (5 minutes) long; a short clip of clean speech is sufficient.
reference_textstringOptional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.nullable
enable_safety_checkerbooleanAuthorized callers may set false to request relaxed screening.default: true

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/qwen-3-tts/clone-voice/0.6b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}