GET

/v1/schemas/fal/video/fal-ai%2Fheygen%2Fv3%2Fvideo-agent

kind inputactivity videohash 2dffb340extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

7 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringNatural language prompt describing the video to generate. The agent handles avatar selection, script, and production automatically.length ≤ 10000
avatarenumAvatar 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"
orientationenumVideo orientation. Auto-detected from the prompt if omitted.landscape | portrait · nullable
style_idstringStyle template ID from the /v3/video-agent/styles endpoint.nullable
voiceenumVoice 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"
incognito_modebooleanWhen enabled, disables the agent's memory functions.default: false
file_urlsstring[]URLs of files to include as assets in the video (images, videos, audio, PDFs). Maximum 20 files.items ≤ 20 · 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", …}]}