GET

/v1/schemas/fal/audio/fal-ai/vibevoice/0.5b?kind=output

Accept:

kind outputactivity audiohash f2e78082…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `6688a703e11361065b9e2dadbc2eb44304397a0b919735dd749d2c9046fce20c` { "fetchedAt": 1783331098, "extractorVersion": "1", "verifiedAt": null }

Response body

5 properties · 5 required · 1 $defs

property	type	description
rtf*	number	Real-time factor (generation_time / audio_duration). Lower is better.
generation_time*	number	Time taken to generate the audio in seconds
audio*	File	The generated audio file containing the speech
sample_rate*	integer	Sample rate of the generated audio
duration*	number	Duration of the generated audio in seconds

Types

1 $defs

Fileobject

file_name	string	The name of the file. It will be auto-generated if not provided.	nullable
content_type	string	The mime type of the file.	nullable
url*	string	The URL where the file can be downloaded from.
file_size	integer	The size of the file in bytes.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/vibevoice/0.5b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}