> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openwhispr.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> OpenWhispr is an open-source voice-to-text dictation app with AI agents, meeting transcription, and notes. Available on macOS, Windows, and Linux.

OpenWhispr turns your voice into text, notes, and actions. It runs on your desktop with local or cloud speech recognition, an AI agent you can talk to, live meeting transcription, and a full notes system with semantic search.

## What you can do

<CardGroup cols={2}>
  <Card title="Dictation" icon="microphone" href="/guides/dictation">
    Press a hotkey, speak, and your words appear at your cursor. Works in any app.
  </Card>

  <Card title="AI agent" icon="robot" href="/guides/agent-mode">
    Talk to your AI assistant using OpenAI, Anthropic, Google, or local models.
  </Card>

  <Card title="Meeting transcription" icon="users" href="/guides/meeting-transcription">
    Auto-detect Zoom, Teams, and FaceTime calls. Transcribe with speaker labels.
  </Card>

  <Card title="Notes" icon="note-sticky" href="/guides/notes">
    Create, organize, and search notes with folders, cloud sync, and AI actions.
  </Card>
</CardGroup>

## Processing options

Choose how your audio is processed:

* **OpenWhispr Cloud** — sign in and transcribe instantly, no API keys needed
* **Bring your own key** — use your own OpenAI, Groq, xAI, Mistral, Tinfoil, OpenRouter, or Corti credentials
* **Local processing** — download Whisper or NVIDIA Parakeet models for completely private transcription

## Platforms

OpenWhispr runs on macOS 12+, Windows 10+, and Linux. Download from the [releases page](https://github.com/OpenWhispr/openwhispr/releases/latest) or build from source.

<CardGroup cols={3}>
  <Card title="macOS" icon="apple" href="/platform/macos">
    Apple Silicon and Intel
  </Card>

  <Card title="Windows" icon="windows" href="/platform/windows">
    x64 with push-to-talk
  </Card>

  <Card title="Linux" icon="linux" href="/platform/linux">
    AppImage, deb, rpm, tar.gz
  </Card>
</CardGroup>

## For developers

OpenWhispr has a public REST API and an MCP server for AI assistant integration.

<CardGroup cols={2}>
  <Card title="API reference" icon="code" href="/api/overview">
    Manage notes, folders, transcriptions, and usage programmatically.
  </Card>

  <Card title="MCP server" icon="plug" href="/integrations/mcp">
    Connect Claude, Cursor, or VS Code to your OpenWhispr data.
  </Card>
</CardGroup>