Text-Driven Lip Sync
Write the script, choose a reusable avatar, and create a talking video without uploading source audio.
Script
Or try a sample prompt
Duration
7
Voice asset ID
Avatar asset ID
Clarity
Aspect ratio
Select model
Preview
No result yet
Preview task status and the generated talking video without leaving the workspace.
Video / Text-Driven Lip Sync
mcp_tool_id
remote_mcp_endpoint
https://medux.io/api/mcp/v1Invocation Example
Create a 7 second 1080P 16:9 talking video from this script using avatar_asset_id {avatar_asset_id}, voice_asset_id {voice_asset_id}, and model_id talking-video-text-standard.
medux_video_create_text_drivenResult: video
avatar_asset_id{avatar_asset_id}voice_asset_id{voice_asset_id}text{script}model_idtalking-video-text-standard