GET

/v1/schemas/fal/video/minimax/h3-max/lip-sync/image-to-video?kind=output

Accept:

kind outputactivity videohash 3c543516…extracted Sep 19, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `733d60d896f94ea8b370fd2cd5d6997b61278f5d17ca1f952e0a975fa0f47b10` { "fetchedAt": 1789794055, "extractorVersion": "1", "verifiedAt": null }

Response body

4 properties · 3 required · 1 $defs

property	type	description	constraints
video*	File	Lip-synced video with the supplied soundtrack.
duration*	number	Output duration in seconds.
seed*	integer	Random seed used for generation.
timings	object	Timing breakdown in seconds. 'inference' is the DiT denoising time on the GPU backend, summed over every window this request generated. Null on routes that do not report backend timings.	nullable

Types

1 $defs

Fileobject

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

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"minimax/h3-max/lip-sync/image-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}