Getting Started

1. Download and install

Download the latest build for your platform from the GitHub Releases page.

These are unsigned developer previews.Code-signing certificates aren’t provisioned yet, so macOS and Windows will both object on first launch. Neither download is broken — the steps below get you past it.

macOS: “edytlab is damaged and can’t be opened”

The app is not damaged. macOS attaches a quarantine flag to anything downloaded from the internet, and refuses to launch a quarantined app that Apple hasn’t notarized. Because the refusal is phrased as damage, the dialog offers only Move to Trash— there is no “Open Anyway” button to click, and right-click → Open will not help either.

Remove the flag after dragging the app to Applications:

xattr -dr com.apple.quarantine /Applications/edytlab.app

Then open it normally. You only need to do this once per install. If you see a milder “unidentified developer” message instead, System Settings → Privacy & Security → Open Anyway is enough on its own.

This goes away once notarization is set up; until then every release needs the command above.

Windows: SmartScreen

Click “More info” → “Run anyway” on first launch. SmartScreen reputation is earned through download volume and cannot be shortcut, so this warning persists until the installers are signed.

2. Get an API key

edytlab uses an LLM to understand your editing instructions. You bring your own API key — it is stored in your OS keychain and never sent to edytlab servers.

Cost estimate: A typical 30-minute editing session consumes roughly $0.05–0.50 in LLM tokens depending on the model and session complexity. Haiku / GPT-4o mini cost ~10× less than Sonnet / GPT-4o.

3. Enter your API key

1. Launch edytlab.
2. Click the gear icon (⚙) in the top-right corner.
3. Select your provider (Anthropic, OpenAI, Gemini, Groq or OpenRouter) from the dropdown.
4. Paste your API key into the field and press Save.
5. edytlab validates the key immediately with a 1-token test request. A green checkmark means you are ready.

Keys are stored using your OS native keychain (macOS Keychain, Windows Credential Manager). They are never written to disk or sent to any edytlab server.

4. Load your first audio file

There are three ways to load audio:

• Drag and drop — drag an MP3, WAV, or FLAC file directly onto the timeline area. Drag multiple files at once to create a multi-track session automatically.
• Open button — click "Open Audio" in the empty state or the file menu.
• Chat — type a message like load /path/to/file.wav in the chat panel.

Once loaded, the waveform appears in the timeline and the session is ready for editing.

5. Your first edit

Type in the chat panel. Describe what you want in plain English — the agent figures out which tools to run.

Example prompts to try:

• Remove the silence at the beginning
• Normalize to -14 LUFS
• Separate the stems
• Transcribe this audio
• Export to /Users/me/Desktop/output.wav

The agent streams its response in real time, showing tool call badges as it executes each operation. Every change creates a new node in the session graph — nothing is destructive.

6. Undo and redo

Every edit is stored as a node in a directed acyclic graph (DAG). You can undo and redo freely:

• Ctrl+Z (Cmd+Z on Mac) — undo
• Ctrl+Y (Cmd+Y on Mac) — redo

Unlike a linear undo stack, the DAG preserves all branching history. You can fork a session, try a different edit, and switch between branches using the Graph view.

Keyboard shortcuts

Press ? at any time to see the full shortcuts overlay. Key shortcuts:

Next steps

• User Guide — full coverage of every feature
• Audio Tools Reference — all 69 tools the agent can call
• Developer Guide — build from source, run tests, contribute