edytlabDocumentation
Everything you need to use edytlab and build on top of it.
Getting Started
Install edytlab, set up your API key, and load your first audio file in under 5 minutes.
User Guide
Sessions, the DAG, tracks, chat interface, markers, A/B compare, export, memory, and skills.
Audio Tools Reference
All 33 tools the agent can call — cut, normalize, stem separate, transcribe, render, and more.
Developer Guide
Build from source, run tests, understand the architecture, and contribute new tools or providers.
API Reference
Every Tauri command, TypeScript bridge type, and SSE event — complete with signatures and examples.
About edytlab
edytlab is a local-first, open-source desktop audio editor where you chat with an AI agent to load, cut, mix, transcribe, and render audio. The DSP engine runs entirely on your machine — your audio never leaves your device. The only network traffic is the text tokens you send to your chosen LLM provider.
edytlab supports three LLM providers out of the box: Anthropic, OpenRouter, and OpenAI. You bring your own API key, stored in your OS keychain. You can switch providers at any time from Settings without reinstalling.
Platform support
| Platform | Status | Minimum version |
|---|---|---|
| macOS (Apple Silicon) | ✅ Supported | macOS 11.0 (Big Sur) |
| macOS (Intel) | ✅ Supported | macOS 11.0 (Big Sur) |
| Windows | ✅ Supported | Windows 10 (with WebView2) |
| Linux | 🔜 Planned (post-v1) | Ubuntu 22.04+ |
License and source
edytlab is open source. View the source on GitHub. License is TBD — will be committed before public distribution.