Voice becomes text. Talk to any MCP server. Cross-platform.
Hold fn in any editable field. T2T records while you hold the key, transcribes the audio locally with Whisper, and inserts the result into the field you were using.
Hold fn+ctrl
to send the transcript to the local pi CLI. Configure the provider, model, voice output, and MCP servers in Settings; the agent runs on your Mac.
Connect to databases, APIs, filesystems. The agent uses tools from your MCP servers. Unlimited extensibility.