Skip to main content
MCP server CX Codex

Audo — Claude Code MCP server: what it does, how to install

Processes audio and video through AI assistants to strip noise, cut dead air, level voices, and generate speech transcripts. Useful for editing media straight from code.

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http audo https://audo.ai/mcp
Open on GitHub

What Audo does

Audo runs as a remote HTTP MCP endpoint hosted at https://audo.ai/mcp. There are no local dependencies. Authentication relies on OAuth: your assistant opens an audo.ai browser window on the first call.

The server provides tools to scrub background hum, improve muffled speech, delete filler words, drop silent gaps, and combine voice tracks with background audio. For speech-to-text, it handles 60 languages with speaker diarization and outputs SRT or VTT caption files. Media files enter processing through URL imports or direct file uploads.

Uploaded files are deleted after 24 hours. The service grants a daily free quota for each tool, charging per audio minute only for jobs that finish successfully.

What it helps with

  • strip background hum and room echo from voice tracks
  • produce SRT or VTT transcripts across 60 languages with speaker tags
  • slice out hesitations, filler sounds, and empty pauses
  • combine voice tracks with background audio and balance loudness

Example prompts for the agent

  • Use Audo to filter background hiss out of demo-voice.wav.
  • Generate an SRT transcript for review.mp4 with speaker labels.
  • Remove silent gaps and normalize audio levels in discussion.m4a.

How to install Audo

Platform CLI: remote server

claude mcp add --transport http audo https://audo.ai/mcp

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Audo

How to install Audo in Claude Code?

Run claude mcp add --transport http audo https://audo.ai/mcp in your terminal. On the first tool call, approve the OAuth sign-in request.

What languages does Audo support for transcription?

The transcribe_audio tool handles 60 languages, producing SRT or VTT files with speaker labels and word timestamps.

How long are uploaded media files retained?

Uploaded media is permanently removed after 24 hours, so keep your raw source files saved on your machine.

Similar MCP servers

All MCP servers for AI and ML →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor