GET

/v1/schemas/fal/audio/fal-ai/qwen-3-tts/clone-voice/0.6b?kind=output

kind outputactivity audiohash 446fe41b…extracted Oct 16, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
7218b99633a843f0fb83e8f0c885a90dc513ad0b6bc74740d72f7fb3af50fcd1
{
  "fetchedAt": 1792126843,
  "extractorVersion": "1",
  "verifiedAt": null
}

Response body

1 properties · 1 required · 1 $defs
propertytypedescriptionconstraints
speaker_embedding*FileThe generated speaker embedding file in safetensors format.

Types

1 $defs

Fileobject

url*stringThe URL where the file can be downloaded from.
file_sizeintegerThe size of the file in bytes.nullable
file_namestringThe name of the file. It will be auto-generated if not provided.nullable
content_typestringThe mime type of the file.nullable

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", …}]}