Audio-Driven Lip Sync
Choose a reusable avatar, upload narration audio, and create a lip-synced video in the same workspace.
Upload narration audio
Click/drag to upload
Supports MP3, WAV, M4A, no more than 50MB
Or start from a ready-made reference
Duration
7
Avatar asset ID
Need an avatar ID? First, clone an avatar from a video or from an image. After the clone is complete, open Assets, copy its avatar_id, and paste it below.
Clarity
Aspect ratio
Select model
Preview
No result yet
Preview task status and the generated talking video without leaving the workspace.
Video / Audio-Driven Lip Sync
mcp_tool_id
remote_mcp_endpoint
https://mcp.medux.io/api/mcp/v1Invocation Example
Create a 7 second 1080P 16:9 talking video using avatar_asset_id {avatar_asset_id} and audio_file_id {audio_file_id}. Use model_id talking-video-audio-standard.
medux_video_create_audio_drivenResult: video
avatar_asset_id{avatar_asset_id}audio_file_id{audio_file_id}model_idtalking-video-audio-standard