GET

/v1/schemas/fal/audio/fal-ai/vibevoice/0.5b

Accept:

kind inputactivity audiohash 316768f2…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `aaa1eb8b97551c70dff78f437013efd3862969c88f240ea4a81bbc4b9030d347` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 2 required · 0 $defs

property	type	description	constraints
speaker*	enum	Voice to use for speaking.	Frank \| Wayne \| Carter \| Emma \| Grace \| Mike
script*	string	The script to convert to speech.	length ≤ 90000
cfg_scale	number	CFG (Classifier-Free Guidance) scale for generation. Higher values increase adherence to text.	1 ≤ n ≤ 2 · default: 1.3
seed	integer	Random seed for reproducible generation.	nullable
enable_safety_checker	boolean	Authorized 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/vibevoice/0.5b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}