A free, open-source multitrack audio editor and recorder for macOS, Windows, and Linux — built in C++ on JUCE, with local stem separation and AI-agent control over MCP.
Last verified · 2026-10-02 · by Moe Ameen
Audionaut is a free, open-source multitrack audio editor and recorder for macOS, Windows, and Linux, created by a developer who goes by kvoltmer. Its code base went open source on August 15, 2026 under the GPLv3 license — the project's dual-license model also names a commercial license, but its own license notes say that option isn't actually available yet, pending agreements for the GPL/AGPL-linked third-party libraries it uses. It is built in modern C++ on the JUCE framework and runs natively on all three desktop platforms, positioned as a focused, lightweight editor rather than a full digital audio workstation.
The workflow stays close to a regions-to-playlist-to-export model: record or import audio, mark named regions, drop them into a playlist, and export. Underneath are precise cutting and trimming, multi-channel support, flexible I/O routing, time-stretch from roughly ×0.25 to ×4, and an open JSON project format. Export covers WAV, AIFF, MP3 (via LAME), FLAC, and Ogg Vorbis.
Two features set it apart. Stem separation splits a clip into drums, bass, vocals, and other using demucs.cpp, running entirely on your machine so the audio never leaves your computer. And an Auto Edit feature uses on-device musical analysis — beat tracking, onset detection, and segmentation — to cut and arrange clips.
The headline capability is that AI agents can drive it. Audionaut ships a Model Context Protocol (MCP) server with roughly two dozen tools, so Claude and other MCP-capable agents can operate the editor conversationally while it stays open on screen, with each edit landing as a single, visible undo step.
Audionaut is where the audio gets made; [Kompozy](/) is where that audio becomes a published content campaign. Treat them as two halves of one pipeline. Audionaut's real strength is a fast, local, scriptable editor — and because it is agent-drivable over MCP, you can even have Claude do the repetitive cutting, fading, and arranging for you. But once you have a clean episode, voiceover, or track, Audionaut has done its job: it exports a file and nothing more. The step that actually earns reach — turning that recording into clips, video, and posts across every platform — is exactly what Kompozy automates.
Hand Kompozy the finished recording (or the video you captured alongside it) and it fans the ideas into formats an audio editor can't make: [Clipped Shorts](/glossary/clipped-short) cut vertical highlights from the long recording, [Persona Shorts](/glossary/persona-shorts) and HeyGen avatar video build a talking-head trailer, brand-exact [Carousel Posts](/glossary/hyperframes) and Quote Graphics surface the strongest lines, and the transcript becomes a Blog Article of show notes plus an Email Newsletter. A [Persona Brief](/glossary/persona-brief) holds one voice and your banned words across all of it, and [Autopilot](/glossary/autopilot) with a per-post review step schedules and publishes the batch across eight social platforms plus blog and email from a single queue. Audionaut produces the audio; Kompozy produces and ships everything around it.
Audionaut is a free, open-source multitrack audio editor and recorder for macOS, Windows, and Linux, built in modern C++ on the JUCE framework. It handles recording, cutting, regions and playlists, multi-channel editing, time-stretch, local stem separation, and broad export — and it can be driven by AI agents over the Model Context Protocol (MCP).
With the app open and Node.js 18+ installed, run `claude mcp add audionaut -- npx -y audionaut-mcp`. Claude can then create projects, split and move clips, adjust gain, speed, and fades, name regions, run beat detection, separate stems, and assemble arrangements conversationally, with each edit appearing as a single undo step in the UI.
Yes — it went open source on August 15, 2026 under GPLv3 and is free across all three desktop platforms. A commercial license is on the project's roadmap but, per its own license notes, not yet actually available. The honest limits are that it is a young project with a leaner feature set than a mature DAW, and it is an editor only: it produces audio files, not captions, video, or published posts.
Audionaut exports the audio but does not publish it. Bring the finished recording into Kompozy to cut Clipped Shorts and Listicle Video, generate a HeyGen persona trailer, build a brand-exact carousel and quote graphics, write show notes as a blog and a newsletter from the transcript, and schedule and publish across eight social platforms plus blog and email from one queue.