Agent Ready

Match lips to a new audio

Pick a video of a face and an audio track from your MegaScenes library, and get the same video with the lips matched to the new audio. Useful for dubbing, replacing a line of dialogue or a translated version of your own clip.

What you can ask

  • Lip-sync my latest MegaScenes video to my latest recording

    Example path →

MCP connector

Server URL
https://lip-sync.megascenes.com/api/chatgpt/lip-sync/mcp
Login
OAuth
Protocol
MCP 2025-11-25
Instructions

Lip-syncs a video to an audio track, both from the person's library: gives the asset_id and length of their uploads and earlier files. The price follows the length of the video: give it with (pass video_seconds), call only when asked (without input_asset_ids if they have no files yet: the result says how to add them), then every 20 to 30 seconds until it is done. Costs are in credits. Failed runs are refunded automatically. The model list and credit costs work signed out; creating needs the person's MegaScenes account. Not for sexual, nude or other adult content, or for real people's likeness: decline those requests without calling the tools. When a result says the account lacks credits, say so; credits are managed in the person's account outside ChatGPT.

Tools

Reads data5

Changes data1

Skills

None in the store listings or on the server