1
Copy the CleanAudio connector URL
You'll paste this URL into Claude in the next step
Podcast editing through a hosted MCP connector
Connect your agent to CleanAudio, sign in with your account, and clean, trim, join, transcribe, or add TTS to podcast workflows with no self-hosted audio stack
MCP
2
Go to Claude → Customize
In Claude desktop or claude.ai, go to Customize → Connectors. Name it CleanAudio and paste the URL
3
Connect, sign in and start
Sign in, then ask Claude to clean, cut, or transcribe audio
CleanAudio's podcast editing MCP gives AI agents concrete podcast tools: clean_noise for background noise, remove_silence for dead air, cut_audio for trims, join_audio for takes, text_to_speech for narration, and transcribe for show notes.
Paste the hosted connector URL into Claude, Cursor, ChatGPT, or a compatible VS Code MCP client, then authorize your CleanAudio account.
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
- Prepare podcast show-note text with transcribe
Example prompts
Ask Claude, Cursor, ChatGPT, or VS Code in plain language.
- “Remove background noise from this podcast interview.”
- “Remove silence, then trim the first 20 seconds.”
- “Join the intro, interview, and outro in that order.”
- “Transcribe this episode for show notes.”
- “Create a short TTS episode disclaimer.”
- “Clean this remote guest recording before I publish it.”
Concrete podcast tasks for your agent
Clean remote recordings
Use clean_noise to improve interview, voice-note, and guest audio.
Tighten the pacing
Remove silence and cut unwanted intros or endings from a spoken episode.
Create supporting text
Use transcribe for a draft transcript or ask for TTS narration where it fits.
Edit a podcast with CleanAudio MCP
Connect once, authorize your account, and let an agent coordinate the audio cleanup steps.
- 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
Connect your AI agent
Add the URL in Claude Connectors, Cursor Settings → MCP, ChatGPT connectors, or your VS Code MCP client.
- 3
Sign in to CleanAudio
Complete the browser sign-in with your CleanAudio account. Authorization keeps processing and usage tied to your account.
- 4
Ask for podcast editing
Upload or reference your audio, then give the agent a concrete instruction. It can choose the relevant CleanAudio tool.
Tools your agent can call
The hosted podcast workflow uses clean_noise, cut_audio, join_audio, text_to_speech, remove_silence, and 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
More audio workflows for podcast creators
CleanAudio MCP hub
Connect an AI agent to CleanAudio's hosted audio tools.
MCP connector documentation
See setup guidance and the available CleanAudio MCP tools.
Claude MCP for audio
Use the same hosted connector from Claude.
Cursor MCP for audio
Run CleanAudio tools from the Cursor agent.
Remove silence MCP
Explore another focused CleanAudio MCP workflow.
CleanAudio Podcast Editing MCP FAQ
It exposes tools for noise cleanup, cuts, joins, silence removal, TTS, and transcription.
Yes. Ask the agent to use clean_noise on the uploaded interview recording.
Yes. The transcribe tool can create text from a podcast recording.
Yes. Ask the agent to use remove_silence before further edits or publishing.
No for these hosted MCP tools. Add the remote connector and sign in to CleanAudio.
Start podcast editing from your agent
Add the hosted CleanAudio MCP connector, sign in once, then send a clear audio request from your preferred agent.