video-to-video-lip-sync
Video To Video Lip Sync is ByteDance's video to video model, available here through a single relay API. It restyles or edits an existing video. Provide a source video plus a prompt describing the change. Requests run server-side against 97AI.PRO with your credit balance, so you get ByteDance quality without managing a separate ByteDance account or key.
Service mode: lite for frontal videos, basic for complex scenes
Video URL (360p-1080p; MOV, MP4, HDR; max 500MB)
Target audio URL to drive lip movements; max 10MB
Enable vocal separation to suppress background noise
Enable scene segmentation and speaker ID (basic mode only)
Loop video when audio is longer than video (lite mode)
Loop video backward; requires align_audio=true (lite mode)
Start time of template video in seconds (lite mode)