English Français العربية

Audo

Registre officiel Médias et design

Audio and video tools for your AI assistant: remove noise, enhance voices, transcribe, and more.

Code source Site web Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http audo 'https://audo.ai/mcp'
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "audo": {
            "type": "http",
            "url": "https://audo.ai/mcp"
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. Audo MCP server
  2. Add it
  3. Tools
  4. Free use and pricing
  5. Example prompts
  6. Links
  7. Support

Audo MCP server

Audo is a set of audio and video tools for you and your AI assistant: remove noise, enhance voices, transcribe, cut, and more. Pro sound, without the studio.

This repository documents Audo's hosted MCP server at https://audo.ai/mcp. It works over streamable HTTP. Sign-in is OAuth: the first time you use it, your assistant asks you to sign in at audo.ai. The repository also holds the server.json entry for the official MCP Registry, ai.audo/audo.

Add it

Claude Code

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

Any MCP client

{
  "mcpServers": {
    "audo": {
      "url": "https://audo.ai/mcp"
    }
  }
}

Setup guides for ChatGPT, Claude, and other assistants: https://audo.ai/setup?utm_source=github&utm_medium=directory

Tools

ToolWhat it does
remove_noiseClears the background, keeps your voice.
enhance_voiceMakes any recording sound studio-quality: echo, muffled, and phone voices.
transcribe_audioSpeech to text, who said what: 60 languages, SRT and VTT captions, word times.
align_scriptSyncs a script to audio, for captions.
remove_fillersCuts the ums and uhs.
remove_silenceCuts out long pauses.
cut_audioTrims the start, middle, or end.
join_audioMerges files into one.
mix_tracksLayers voices and music.
replace_audioNew sound, same picture.
adjust_loudnessMakes quiet audio louder.
level_speakersEvens out loud and quiet voices.
convert_audioAudio to MP3, WAV, and more.
analyze_audioLength, format, and more.

Files and jobs: create_upload, import_file (fetches a direct file URL), list_files, get_file, get_job, get_download, get_transcript, cancel_job, and get_account. Uploaded files are deleted after 24 hours.

Free use and pricing

Every tool has a free part each day, with no payment. Beyond it, you pay per minute of audio, and only for jobs that succeed. Prices: https://audo.ai/pricing?utm_source=github&utm_medium=directory

Example prompts

  • Use Audo to remove the background noise from interview.wav.
  • Use Audo to transcribe meeting.mp4 with speaker labels and give me SRT captions.
  • Use Audo to make voice-note.m4a sound like it was recorded in a studio.
  • Use Audo to cut the first 30 seconds from podcast.wav.

Support

support@audo.ai

Questions fréquentes

Qu'est-ce que Audo ?

Audio and video tools for your AI assistant: remove noise, enhance voices, transcribe, and more.

Comment installer Audo ?

Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http audo 'https://audo.ai/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Audo ?

Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.

Audo est-il open source ?

Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.

Qui maintient Audo ?

Il est publié par audo-ai. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.