Model IDDocumentation Index
Fetch the complete documentation index at: https://docs.gmicloud.ai/llms.txt
Use this file to discover all available pages before exploring further.
Kling Advanced Lip Sync
Generates a new video where the selected face(s) in the source video are lip-synced to a user-supplied audio clip. Builds on top of thekling-identify-face analysis pass.
Typical Workflow
- Run
kling-identify-faceon your source video to obtain asession_idand the list of detectedface_ids. - Submit
kling-lip-syncwith thatsession_idand aface_choosearray selecting which face(s) to drive and the audio to use.
face_choose Schema
face_choose is forwarded verbatim to Kling and must follow Kling’s native format:
face_id(string): one of the IDs returned bykling-identify-face.sound_file(URL): the audio clip to lip-sync to.sound_insert_time(ms): position in the source video where the audio is inserted.sound_start_time/sound_end_time(ms): clip window inside the audio file.sound_volume/original_audio_volume: relative mix levels.
API Usage
Submit a generation task via the GMI request queue. Polling and full parameter docs are in the API reference.Submit request
request_id. Poll the status endpoint until the video is ready, then download from the returned URL.