Audo

Audo MCP server and agent plugin

Audo: pro sound without the studio. Audio and video tools for you and your AI assistant: remove noise, enhance voices, transcribe, cut, and more.

This repository packages Audo's hosted MCP server at https://audo.ai/mcp. It uses Streamable HTTP and OAuth. The first time you connect, your assistant asks you to sign in to your Audo account. No API key is required for the OAuth connection (clients that cannot open a browser can send an API key from audo.ai/keys as a Bearer token).

Install

Agent Plugin and Gemini CLI extension clients

This repository contains a portable Agent Plugins manifest (plugin.json), a Gemini CLI extension manifest (gemini-extension.json), and a root mcp.json pointing to the hosted server. Install the repository using your client's plugin or extension workflow. Official marketplace listings are pending; this repository does not imply approval by a marketplace.

Claude Code

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

Codex

codex mcp add audo --url https://audo.ai/mcp

codex mcp login audo

Gemini CLI

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

GitHub Copilot CLI

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

Cursor and other MCP clients

For a client's custom MCP configuration, use:

{

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

Connect through OAuth when the client prompts. See setup guides for client-specific instructions.

What it does

• Speech cleanup: remove_noise reduces background noise while preserving the recorded voice. enhance_voice regenerates supplied speech to restore echo, distortion, muffled recordings, and poor microphones. Both are designed for speech and can remove music or other sounds.
• Transcription, translation, and shortening: transcribe_audio produces text, word timestamps, speaker labels, and TXT/SRT/VTT/JSON outputs. align_script aligns an existing script to a recording. translate_transcript translates speech transcripts while keeping segment times and speakers, and translate_subtitles translates SRT/VTT files into up to 5 languages. find_highlights ranks moments for short clips, and shorten_transcript condenses speech in source order with waveform-safe cut ranges and retimed captions.
• Captions, audiograms, and overlays: add_captions burns styled captions into video (with presets from list_caption_presets, saved styles via save_caption_style, keyword highlighting, auto-emoji, translation, and bilingual options). audio_to_video turns audio into an MP4 audiogram with reactive waveforms (with presets from list_audiogram_presets). add_overlay adds timed text and logo overlays with animations.
• Editing: cut_audio, remove_fillers, remove_silence, and join_audio trim recordings, remove filler words or long pauses, and combine files.
• Finishing: level_speakers balances loud and quiet voices; mix_tracks layers and ducks tracks; adjust_loudness sets a target loudness; convert_audio changes audio formats; replace_audio swaps a video's soundtrack.
• Video and reframing: reframe_plan and reframe_video track faces across scenes to reframe video into 9:16, 1:1, 4:5, or 16:9 with editable keyframe plans. convert_video, compress_video, crop_video, resize_video, reverse_video, loop_video, mute_video, get_frame, and video_to_gif convert, compress, crop, resize, reverse, loop, mute, extract still frames, and turn clips into animated GIF or WebP files.
• Music and stems: split_audio separates vocals, instrumental, 4-stem, or dialogue/music/effects stems; change_speed_pitch changes tempo and pitch; find_key_bpm measures musical key and BPM; reverse_audio reverses sound.
• Analysis: analyze_audio reports media information, integrated LUFS loudness, true peak, noise floor, clipping, and silence.

Use add_file for a direct HTTPS file URL, a chat attachment, or to start an upload. Supported chat clients also expose Audo's in-chat upload box. Local coding agents can use the returned upload command. Do not pass a local filesystem path as a public URL.

list_files, get_file, get_job, get_transcript, cancel_job, and get_account manage files, status, transcript reading, cancellation, and account information. Processing tools return either finished output or a job to check with get_job.

Example workflows

• Remove background noise from an interview and return the cleaned recording.
• Balance a quiet guest and loud host, then normalize the result for a podcast.
• Transcribe a recording with speaker labels, translate subtitles, or burn styled captions into a video.
• Reframe a horizontal talk into a 9:16 vertical clip following the speaker's face, or turn an audio clip into a waveform audiogram.
• Shorten a meeting recording or extract ranked highlight clips.
• Split vocals and instrumental audio, then change the instrumental's speed or pitch.

Free use, limits, and privacy

Tools include a free allowance subject to per-tool daily limits. Full-file processing beyond that allowance requires sufficient existing Audo credits. Current allowances and rates are on Audo's pricing page.

Files and results are deleted after 24 hours. Output download links are temporary; use get_file for a fresh link while the file is retained. Only upload recordings you are permitted to process. See privacy and terms.

Documentation and support

• MCP documentation
• API documentation
• Agent-readable tool index
• Support · support@audo.ai

The repository also contains server.json for the official MCP Registry entry ai.audo/audo. The hosted service is operated by Audo AI LLC; its implementation and credentials are not included here.