GET

/v1/schemas/fal/video/fal-ai%2Fkling-video%2Flipsync%2Ftext-to-video

kind inputactivity videohash c95a3169extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

5 properties · 3 required · 0 $defs
propertytypedescriptionconstraints
text*stringText content for lip-sync video generation. Max 120 characters.length ≤ 120
video_url*stringThe 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*enumVoice ID to use for speech synthesisgenshin_vindi2 | zhinen_xuesheng | AOT | ai_shatang | genshin_klee2 | genshin_kirara · +40 more
voice_languageenumThe voice language corresponding to the Voice IDzh | en · default: "en"
voice_speednumberSpeech rate for Text to Video generation0.8 ≤ n ≤ 2 · default: 1

Validate a payload

before you spend tokens
shell
$ 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", …}]}