GET

/v1/schemas/fal/video/fal-ai/kling-video/lipsync/text-to-video

Accept:

kind inputactivity videohash 0a5f79b6…extracted Oct 14, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `01218fcb958a94b312f8581b7afa72964879bbe448d03187edbdfd51fd6acba3` { "fetchedAt": 1791954060, "extractorVersion": "1", "verifiedAt": null }

Request body

6 properties · 3 required · 0 $defs

property	type	description	constraints
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.
text*	string	Text content for lip-sync video generation. Max 120 characters.	length ≤ 120
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
enable_safety_checker	boolean	Disabling safety checks requires account authorization; unauthorized requests are always checked.	default: true

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", …}]}