GET
/v1/schemas/fal/video/fal-ai%2Fkling-video%2Flipsync%2Ftext-to-video
Accept:
Request body
5 properties · 3 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| text* | string | Text content for lip-sync video generation. Max 120 characters. | length ≤ 120 |
| video_url* | string | The URL of the video to generate the lip sync for. Supports .mp4/.mov, ≤100MB, 2-60s, 720p/1080p only, width/height 720–1920px. If validation fails, an error is returned. | |
| voice_id* | enum | Voice ID to use for speech synthesis | genshin_vindi2 | zhinen_xuesheng | AOT | ai_shatang | genshin_klee2 | genshin_kirara · +40 more |
| voice_language | enum | The voice language corresponding to the Voice ID | zh | en · default: "en" |
| voice_speed | number | Speech rate for Text to Video generation | 0.8 ≤ n ≤ 2 · default: 1 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/kling-video/lipsync/text-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}