GET

/v1/schemas/fal/audio/alibaba/qwen-audio-3-tts?kind=output

Accept:

kind outputactivity audiohash 6b7aebca…extracted Jul 30, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `1cdca83aa0e9b4e455ca652926d6c550c99c187ab2c7258e5d3a176aaaa2366e` { "fetchedAt": 1785387725, "extractorVersion": "1", "verifiedAt": null }

Response body

1 properties · 1 required · 1 $defs

property	type	description	constraints
audio*	AudioFile	The generated speech audio file.

Types

1 $defs

AudioFileobject

sample_rate	integer	The sample rate of the audio	nullable
channels	integer	The number of channels in the audio	nullable
file_size	integer	The size of the file in bytes.	nullable
file_name	string	The name of the file. It will be auto-generated if not provided.	nullable
duration	number	The duration of the audio	nullable
bitrate	string \| integer	The bitrate of the audio (e.g., '192k' or 192000)	nullable
url*	string	The URL where the file can be downloaded from.
content_type	string	The 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":"alibaba/qwen-audio-3-tts","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}