{
  "id": 11415010,
  "title": "Show HN: Audionaut – an open-source cross-platform multitrack audio editor",
  "url": "https://urgent.news/2026/10/02/show-hn-audionaut-an-open-source-cross-platform-multitrack-audio",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-02T08:05:48.000Z",
  "source": {
    "name": "Hacker News",
    "slug": "hacker-news",
    "url": "https://github.com/kvoltmer/Audionaut"
  },
  "original_language": "en",
  "account": "Audionaut is an open-source, cross-platform multitrack audio editor that can be controlled by AI agents over MCP. This free desktop application offers effortless audio editing and recording for music, podcasts, and multitrack recordings. With precise cutting, per-track playlists, flexible multi-channel support, and clean exports, Audionaut stands out for its simplicity compared to full DAWs.\n\nDeveloped in modern C++ using the JUCE framework, Audionaut is available natively on Windows, macOS, and Linux. It communicates with Claude and other agents using MCP, enabling automated editing of sessions. After installing Audionaut and Node.js 18 or higher, one can keep the project open in the app, with each edit recorded as a single undo step.\n\nOn macOS, projects should be stored in the Music folder. The application includes analysis features like BIC segmentation, onset detection, and beat tracking, which link against a static build of the Essentia submodule. After checking out the submodules, running the provided script builds Essentia with its waf build system on macOS/Apple Silicon, ensuring compatibility.\n\nBuilding Essentia is optional, as the app and tests compile with analysis features disabled by default. Stem separation utilizes demucs.cpp, a C++ port of Meta's Demucs, compiled directly from the submodule without a separate build step. Model weights are downloaded on first use into the app's Models folder or can be specified via the CLI with the --model option.\n\nVisual Studio 2026 is required to open the Audionaut solution file, while audionaut-cli provides scripts, CI, and headless AI agent access to .audium projects without a GUI. The CLI generates machine-readable JSON results, with exit codes indicating success (0), operation failure (1), usage errors (2), or unavailable features (3). Command options can be provided as --opt value or --opt=value.\n\nTo use the CLI for an automated agent flow, follow these steps: create → import → analyze → auto-edit/assemble → export, checking the ok status in each JSON envelope. Projects created via CLI open in the GUI app and vice versa. End-user documentation is available in the User Manual, and the CLI reports anonymous usage statistics under opt-in consent, with the main app accepting the same verb commands for headless execution.\n\nAudionaut is dual-licensed under GPL3 (or later) and a commercial license, with contributions welcomed via the CONTRIBUTING.md file and the required Contributor License Agreement (CLA.md). Developers can sponsor the project's development to support its ongoing maintenance and sustainability.",
  "summary": null,
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}