VocalRemover MCP

Ask your assistant to edit audio in plain language — for example, "remove the vocals from this track."

- Remove vocals for karaoke— Get an instrumental backing track viaseparate_audiowith the instrumental task.
- Split songs into stems— Useseparate_audiowith the stems task to get vocals, drums, bass, guitar, and piano.
- Convert audio formats— Convert files between MP3, WAV, FLAC, OGG, M4A, AAC, and OPUS.
- Trim and probe audio— Trim a clip to an exact start time and length, or check duration, bitrate, and format.
- Extract audio from video— Pull the audio track from MP4, MKV, MOV, or AVI files.
- Clean up voice recordings— Denoise and de-reverb recordings to remove background noise and room echo.

Audio MCP Server for Claude, Cursor, ChatGPT & any AI agent

Remove vocals, split stems, clean up recordings and more — right inside Claude, Cursor or ChatGPT. Just say what you want and get the finished file back.

Set it up in under a minute — then let your assistant do the work.

Works with Claude· Cursor· Windsurf· Cline· Zed· ChatGPT · 22 tools · 18 free

Once connected, type what you want — your assistant calls the right tool and hands back a download link.

Remove the vocals from this song and give me the karaoke track.

Called separate_audio · task: instrumental

Done — vocals removed with our HQ Fusion model. Here is your karaoke track:

Now split the original into stems — vocals, drums, bass, guitar and piano.

Split into 5 stems with Multi-stem HQ. Here are your downloads: vocals.mp3 drums.mp3 bass.mp3 guitar.mp3 piano.mp3

Convert this interview to MP3 and clean up the background noise. De-reverb this voice recording. Make an 8D version of this song and trim it to 30 seconds. Extract the audio from this video as a WAV.

"Take these 12 practice recordings, convert each to MP3, then remove the vocals" runs end-to-end in a single agent session — convert, separate, poll, return 12 links. No app-switching, no glue code.

- Convert between MP3, WAV, FLAC, OGG, M4A, AAC and OPUS.
- Trim a clip to an exact start time and length.
- Extract the audio track from any video file.
- Probe a file for its duration, bitrate and format.

- Remove vocals or grab the instrumental for karaoke.
- Split a song into stems: vocals, drums, bass, guitar, piano.
- Clean up voice recordings — remove noise and room echo.
- Track progress and grab results without leaving the chat.

Many audio MCP servers ship older, open-source separation models. We run our own models — the same ones powering vocalremover.com — with a restoration pass on top.

Our flagship separation for cleaner vocals and instrumentals on complex mixes.

Splits a track into vocals, drums, bass, guitar and piano stems.

Restores clarity and detail to processed or low-quality audio.
- 1 Open connector settings In ChatGPT: Settings → Apps → enable Developer mode → Create app, then paste the server URL into the Connection field. In Claude.ai: Settings → Connectors → Add custom connector.
- Drop this address into the connector URL field:

https://vocalremover.com/mcp/audio

For Claude Desktop, Cursor, Windsurf, Cline, Zed and Claude Code — add the server with a Bearer API token.

Create your VocalRemover account, then copy your API token from the API page and paste it into the config below.

Add to claude_desktop_config.json, then restart Claude.

{ "mcpServers": { "vocalremover": { "command": "npx", "args": [ "-y", "mcp-remote", "https://vocalremover.com/mcp/audio", "--header", "Authorization:${AUTH}" ], "env": { "AUTH": "Bearer YOUR_API_TOKEN" } } } }

Native remote MCP — add to the client's mcp.json.

{ "mcpServers": { "vocalremover": { "url": "https://vocalremover.com/mcp/audio", "headers": { "Authorization": "Bearer YOUR_API_TOKEN" } } } }

One command — native remote MCP, no bridge.

claude mcp add --transport http \ vocalremover https://vocalremover.com/mcp/audio \ -H "Authorization: Bearer YOUR_API_TOKEN"

Your audio is fetched from the URL you pass, processed, and deleted — nothing is stored. Your access is scoped to your account and can be revoked any time.

Need details?Read the full documentation

Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.