CleanAudio

Audio editing MCP without a local audio stack

Connect CleanAudio's hosted MCP, sign in with your account, and ask Claude, Cursor, ChatGPT, or VS Code to edit audio with no self-hosting or FFmpeg install

MCP
1

Copy the CleanAudio connector URL

You'll paste this URL into Claude in the next step

2

Go to Claude → Customize

In Claude desktop or claude.ai, go to Customize → Connectors. Name it CleanAudio and paste the URL

Open Claude Customize
3

Connect, sign in and start

Sign in, then ask Claude to clean, cut, or transcribe audio

Start cleaning

CleanAudio provides a hosted audio editing MCP for agents that need to cut clips, join recordings, remove silence, clean noise, generate TTS, or transcribe speech. Paste the connector URL, sign in with your CleanAudio account, and ask your agent for a specific edit.

The available MCP tools are clean_noise, cut_audio, join_audio, text_to_speech, remove_silence, and transcribe.

What this MCP server does

  • Clean background noise with clean_noise
  • Cut an uploaded recording with cut_audio
  • Join ordered clips with join_audio
  • Remove pauses with remove_silence
  • Generate speech with text_to_speech
  • Create a transcript with transcribe

Example prompts

Ask Claude, Cursor, ChatGPT, or VS Code in plain language.

  • “Trim the first 30 seconds from this interview.”
  • “Remove background noise from this voice memo.”
  • “Join these three takes in the order I uploaded them.”
  • “Remove the long pauses from this recording.”
  • “Transcribe this customer interview and return the text.”
  • “Create a short TTS intro for this episode.”

Hosted audio editing for agent workflows

Audio editing studio

Cut and join from a prompt

Ask for a precise trim or ordered join without opening an editing timeline.

CleanAudio account sign-in

Account-based access

Sign in with CleanAudio once instead of storing an audio-processing key in a local config.

Remote MCP tools

One remote toolset

Use the same hosted tools across supported chat and coding agents.

Edit audio through CleanAudio MCP in four steps

The connector is hosted by CleanAudio. Your agent needs only the URL and your CleanAudio sign-in.

  1. 1

    Copy the hosted connector URL

    Copy https://mcp.cleanaudio.app/mcp. CleanAudio hosts the MCP server, so there is no local server or FFmpeg installation.

  2. 2

    Connect your AI agent

    Add the URL in Claude Connectors, Cursor Settings → MCP, ChatGPT connectors, or your VS Code MCP client.

  3. 3

    Sign in to CleanAudio

    Complete the browser sign-in with your CleanAudio account. Authorization keeps processing and usage tied to your account.

  4. 4

    Ask for an audio edit

    Upload or reference your audio, then give the agent a concrete instruction. It can choose the relevant CleanAudio tool.

Tools your agent can call

Use clean_noise, cut_audio, join_audio, text_to_speech, remove_silence, and transcribe through the CleanAudio hosted MCP.

clean_noise

Remove background noise from podcast recordings

cut_audio

Trim MP3 files to create ringtones or clips

join_audio

Merge multiple audio files into one

text_to_speech

Convert blog posts to audio narration

remove_silence

Clean up long recordings by removing pauses

transcribe

Convert speech to text automatically

CleanAudio Audio Editing MCP FAQ

It exposes CleanAudio tools for noise cleanup, cutting, joining, silence removal, TTS, and transcription to an MCP-compatible agent.

No. CleanAudio hosts the connector and processing path. Add the remote URL and sign in.

Yes. Add the same hosted URL in Claude Connectors or Cursor MCP settings, then authorize your CleanAudio account.

Yes. Ask the agent to use join_audio with your clips in the order you need.

The connector opens a browser sign-in for your CleanAudio account. No separate MCP API key is required for this flow.

Start audio editing from your agent

Add the hosted CleanAudio MCP connector, sign in once, then send a clear audio request from your preferred agent.

Open connector setupMCP overview