Kling Lip Sync API
POSThttps://api.acedata.cloud/kling/lip-sync
Kling lip-sync API — sync a character's mouth in a video to audio or text.
Request Headers
authorizationstring
Bearer token
Request Body
modestringRequired parameter
audio2video: Drive with audio clips; text2video: Drive with text + tone.
textstring
Text to be read aloud (required when mode is text2video, up to 120 characters).
asyncboolean
Return task_id immediately when true; you can poll through /kling/tasks or receive callbacks to get the result.
Please select
video_idstring
The ID of the video generated by Kling (for example, from /kling/videos image2video) must be generated within the last 30 days. Choose one of video_url or this.
voice_idstring
The tone used (required when mode is text2video).
audio_urlstring
The public URL for the audio drive (required when mode is audio2video).
video_urlstring
The public URL of the 5-second/10-second video that matches the lip sync. Choose one between video_id.
audio_filestring
Base64 of the audio file (required when audio_type is file). Supports .mp3/.wav/.m4a/.aac, not exceeding 5MB.
audio_typestring
The method of providing audio (for audio2video).
Please select
voice_speednumber
The speech rate of text2video (0.8–2.0, keep one decimal place).
callback_urlstring
If provided (or async=true), it will immediately return task_id and push the result via callback when ready.
voice_languagestring
The tone language of text2video.
Please select
Response
Kling video generation
Allow Use General Balance
When 'Allow General Balance' is enabled, the general balance is used automatically if an app's balance is insufficient.
Kind reminder: For streaming requests, the above code may not be fully applicable. Please refer to the integration documentation for changes.