GET

/v1/schemas/fal/video/fal-ai/heygen/v3/video-agent

Accept:

kind inputactivity videohash 6ffe4909…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `e56d33236d9cc0885b6558219cbfeb91c08153a1036dd3e979f5e32a751c16a4` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 1 required · 0 $defs

property	type	description	constraints
prompt*	string	Natural language prompt describing the video to generate. The agent handles avatar selection, script, and production automatically.	length ≤ 10000
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
file_urls	string[]	URLs of files to include as assets in the video (images, videos, audio, PDFs). Maximum 20 files.	items ≤ 20 · nullable
incognito_mode	boolean	When enabled, disables the agent's memory functions.	default: false
orientation	enum	Video orientation. Auto-detected from the prompt if omitted.	landscape \| portrait · nullable
voice	enum	Voice for narration. Set to 'auto' to let the agent auto-select.	auto \| Warm Pro Narrator \| Chill Brian \| Ivy \| John Doe \| Monika Sogam · +97 more · default: "auto"
avatar	enum	Avatar to use in the video. Set to 'auto' to let the agent auto-select based on the prompt.	auto \| Abigail (Upper Body) \| Abigail Office Front \| Abigail Office Side \| Abigail Sofa Front \| Abigail Sofa Side · +1281 more · default: "auto"
style_id	string	Style template ID from the /v3/video-agent/styles endpoint.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/heygen/v3/video-agent","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}