CleanAudio

Remove silence with a hosted audio MCP

Connect your agent to CleanAudio, sign in with your account, and remove dead air from speech without self-hosting an audio service or installing FFmpeg

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's remove silence MCP workflow gives agents access to remove_silence for recordings with long pauses or dead air. Add the hosted connector, sign in with your CleanAudio account, then ask the agent to tighten the recording and return the result.

You can follow silence removal with clean_noise, cut_audio, join_audio, text_to_speech, or transcribe when needed.

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
  • Tighten spoken recordings with remove_silence

Example prompts

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

  • “Remove silence from this podcast interview.”
  • “Tighten the pauses in this voiceover.”
  • “Remove dead air, then clean background noise.”
  • “Remove silence from each take before joining them.”
  • “Transcribe this recording after removing long pauses.”

Cleaner pacing from your AI agent

Podcast recording cleanup

Speech-focused cleanup

Use remove_silence to reduce dead air in interviews, voice notes, and spoken clips.

Hosted CleanAudio account

Hosted processing

CleanAudio runs the remote MCP service and audio work after account authorization.

Audio post-production workflow

Follow-up edits

Combine silence cleanup with noise removal, cuts, joins, and transcripts in one agent conversation.

Remove silence from audio via MCP

No local audio pipeline is required. Connect, authorize, and ask for a tighter recording.

  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 silence removal

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

Tools your agent can call

Ask your agent to use remove_silence, then continue with clean_noise, cut_audio, join_audio, text_to_speech, or transcribe.

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 Remove Silence MCP FAQ

The CleanAudio MCP exposes remove_silence for agent-controlled dead-air removal.

Silence removal and noise cleanup are separate capabilities. Ask the agent to run clean_noise as an additional step.

Yes. It is useful for tightening pauses in spoken podcast recordings before publishing.

No. CleanAudio hosts it at the connector URL and you sign in with your CleanAudio account.

Use an MCP client with remote HTTP support, such as Claude, Cursor, ChatGPT connectors where available, or compatible VS Code clients.

Start silence removal 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