amicalhq/amical

🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.

What it solves

Amical solves the privacy and efficiency gaps in AI dictation by providing a local-first approach. It allows users to convert speech to text and process notes without sending data to the cloud, while adapting the output format based on the application the user is currently using (e.g., emails, Discord, or IDEs).

How it works

The app runs entirely on the user's machine using a combination of OpenAI's Whisper for high-accuracy speech-to-text and local LLMs (via Ollama) for intelligent processing. It uses a floating widget and custom hotkeys for quick access and integrates with the OS to detect the active application to provide context-aware formatting.

Who it’s for

It is designed for people who want a private, AI-powered voice-to-text tool for note-taking, drafting messages, and productivity across different desktop applications on macOS and Windows.

Highlights

  • Local-first Privacy: Works offline with one-click setup for local models.
  • Context-aware Dictation: Automatically adjusts formatting based on the active app.
  • AI-enhanced Accuracy: Powered by Whisper for fast and precise transcription.
  • Extensible Workflows: Supports hotkeys, voice macros, and custom workflows.
  • Smart Voice Notes: Ability to turn voice notes into summaries, tasks, and structured notes (in progress).
  • MCP Integration: Planned support for voice commands to control other apps.

Related

  • Project
    OpenWhispr/openwhispr

    OpenWhispr is a cross‑platform desktop app that converts speech to text, provides live meeting transcription with speaker diarisation, and lets you talk to AI assistants (GPT‑5, Claude, Gemini, etc.) directly from your keyboard. It works offline with Whisper‑based models or via cloud services, stores notes locally (with optional cloud sync), and offers an API for programmatic use.

  • Project
    Notely-Voice/NotelyVoice

    A private, cross-platform AI voice transcription and note-taking app that uses OpenAI Whisper to provide offline speech-to-text capabilities.

  • Project
    akshayaggarwal99/jarvis-ai-assistant

    An open-source voice dictation tool that converts speech to text anywhere on your system, supporting local transcription and LLM post-processing for privacy and speed.

  • Project
    voquill/voquill

    An open-source, cross-platform AI voice typing app that enables dictation into any desktop application with AI-driven text cleanup and a personal glossary.

  • Project
    tover0314-w/opentypeless

    An open-source AI voice input tool for macOS, Windows, and Linux that provides context-aware dictation, AI rewriting, and one-shot voice Q&A across any desktop application.