Learn how to get the most out of t2t
Download t2t from GitHub Releases. On first launch, you may need to right-click and select "Open" if macOS shows a security warning.
t2t needs two permissions:
The app will prompt you if permissions are missing. You can also grant them in System Settings.
On first launch, t2t automatically downloads the Whisper model (~150MB) to your cache directory. This happens in the background—you'll see a notification when it's ready.
A red bar appears at the top of your screen while recording:
Hold fn + ctrl (or fn + cmd on macOS) to enter agent mode.
A cyan bar appears while recording in agent mode.
Agent mode uses AI to understand your voice command and execute actions:
Agent mode requires an OpenRouter API key:
MCP (Model Context Protocol) servers provide tools and capabilities that extend what the AI agent can do. Instead of hardcoding integrations, you connect to MCP servers that expose their own tools.
Database Server (stdio)
npx @modelcontextprotocol/server-postgres
File System Server (stdio)
npx @modelcontextprotocol/server-filesystem
Remote API Server (HTTP)
https://your-mcp-server.com/api
Use typing mode to quickly input text anywhere:
Connect MCP servers to automate complex workflows:
Without MCP servers, agent mode uses AppleScript for macOS automation:
If t2t isn't detecting the Fn key or can't paste:
If the Whisper model isn't downloading:
~/Library/Logs/t2t.logIf an MCP server won't connect:
If agent mode doesn't respond:
~/Library/Logs/t2t.logNeed more help?