MCP/VocalRemover MCP

VocalRemover MCP

Official VocalRemover audio tools MCP server for AI stem separation, karaoke isolation, audio cleanup, de-reverberation, and format conversion.

video-editing•AI Audio & Vocal Processing

Website

License:Commercial / Free Tier

OFFICIAL

@VocalRemover

About this Server

The official Model Context Protocol server from VocalRemover.com, bringing studio-quality AI audio separation and audio engineering utilities to any MCP client. Ask your AI assistant to remove vocals for karaoke backing tracks with the HQ Fusion model, split songs into five stems (vocals, drums, bass, guitar, piano) with Multi-stem HQ, restore processed voice clarity, denoise and de-reverb speech recordings, extract audio tracks from video files, and convert between MP3, WAV, FLAC, OGG, M4A, AAC, and OPUS formats.

Real-time Interaction

Direct low-latency RPC protocol communication with structured JSON schemas.

Scoped Sandboxing

Restricted capability bounds to prevent accidental modifications or leakage.

Security & Best Practices

Ephemeral Processing: Audio files are fetched from the provided URL, processed by AI models, and immediately deleted without long-term storage.

Account-Scoped Tokens: Access is authenticated via user Bearer tokens that can be revoked at any time from the account settings page.

Zero Model Training on User Data: Uploaded audio tracks and speech samples are never utilized for training proprietary separation models.

Encrypted Streaming: All audio transfers and command execution occur over TLS 1.3 encrypted HTTP streamable endpoints.

When to Use (and When Not To)

Best For

•Isolating vocals or generating instrumental karaoke backing tracks from any song
•Splitting music tracks into individual stems including vocals, drums, bass, guitar, and piano
•Denoising and removing room echo and reverberation from podcasts, voice notes, and interviews
•Converting audio formats, trimming clips to exact intervals, and extracting audio tracks from videos

Not For / Limitations

•Full multi-track MIDI sequencing or virtual synthesizer composition (use a dedicated Digital Audio Workstation instead)
•Real-time low-latency live microphone monitoring or DSP effect pedal emulation
•Local offline processing without internet access to the vocalremover.com processing cluster

Install & Setup

One-line terminal command

terminal command

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

Exposed Tools & Endpoints

7 tools

Functions your AI agent can invoke via this Model Context Protocol server

separate_audio• callable tool

Separate audio into stems or remove vocals using HQ Fusion or Multi-stem HQ models for karaoke, instrumental, vocals, drums, bass, guitar, and piano.

clean_audio• callable tool

Clean up voice recordings by removing background noise and room reverberation using AI denoising and de-reverb models.

restore_vocals• callable tool

Apply Vocal Restoration pass to restore high-frequency clarity, harmonic detail, and fidelity to low-quality or processed vocal tracks.

convert_audio• callable tool

Convert audio files between MP3, WAV, FLAC, OGG, M4A, AAC, and OPUS formats with custom sample rate and bitrate options.

trim_audio• callable tool

Trim an audio clip to an exact millisecond start time and duration with optional fade-in and fade-out envelopes.

extract_audio_from_video• callable tool

Extract the uncompressed or high-bitrate audio track from MP4, MKV, MOV, or AVI video containers.

probe_audio• callable tool

Inspect audio file metadata including duration, channels, sample rate, codec, and average bitrate.