Vocal Remover

Vocals and instrumental apart

Pick a song from your MegaScenes library and get two files back: the instrumental without the voice, ready for karaoke or a cover, and the vocals on their own. Need every part?

What you can ask

Remove the vocals from my latest MegaScenes song
Example path →

MCP connector

Server URL: https://vocal-remover.megascenes.com/api/chatgpt/vocal-remover/mcp
Login: OAuth
Protocol: MCP 2025-11-25
Instructions: Splits a song in the person's library into the instrumental and the vocals: gives the asset_id and length of their tracks. For their own songs, karaoke and practice; it makes no promise about tracks they have no rights to. The price follows the length of the song: give it with (pass video_seconds, the song's length), call only when asked (without input_asset_ids if they have no song yet: the result says how to add one), then every 20 to 30 seconds until it is done. The result has two files, Vocals and Instrumental (six named stems with demucs-stems). 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

MCP connector

Server URL

https://vocal-remover.megascenes.com/api/chatgpt/vocal-remover/mcp

OAuth

Protocol

MCP 2025-11-25

Instructions

Splits a song in the person's library into the instrumental and the vocals: gives the asset_id and length of their tracks. For their own songs, karaoke and practice; it makes no promise about tracks they have no rights to. The price follows the length of the song: give it with (pass video_seconds, the song's length), call only when asked (without input_asset_ids if they have no song yet: the result says how to add one), then every 20 to 30 seconds until it is done. The result has two files, Vocals and Instrumental (six named stems with demucs-stems). 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.