Website - Docs - Community - Bug reports
Local-first AI Dictation app.
Amical is an open source AI-powered dictation and note-taking app that runs entirely on your machine. Powered by Whisper for speech-to-text and open source LLMs for intelligent processing, Amical gives you the power of AI dictation with complete privacy.
Context-aware dictation that adapts to what you're doing: drafting an email, chatting on Discord, writing prompts in your IDE, or messaging friends. Amical detects the active app and formats your speech accordingly.
โ๏ธ - Done, โ - In Progress, โฏ - Planned
๐ Super-fast dictation with AI-enhanced accuracy โ๏ธ
๐ง Context-aware speech-to-text based on the active app โ๏ธ
๐ Smart voice notes โ summaries, tasks, structured notes โ
๐ MCP integration โ voice commands that control your apps โฏ
๐๏ธ Real-time meeting transcription (mic + system audio) โฏ
๐ง Extensible via hotkeys, voice macros, custom workflows โ๏ธ
๐ Privacy-first: works offline, one click setup of local models in-app โ๏ธ
๐ช Floating widget for frictionless start/stop with custom hotkeys โ๏ธ
- ๐ค Whisper
- ๐ฆ Ollama
- ๐งโ๐ป Typescript
- ๐ฅ๏ธ Electron
- โ๏ธ Next.js
- ๐จ TailwindCSS
- ๐ง๐ผโ๐จ Shadcn
- ๐ Better-Auth
- ๐งโโ๏ธ Zod
- ๐ Jest
- ๐ Fumadocs
- ๐ Turborepo
Contributions are welcome! Please read the Contributing Guide to get started.
- ๐ก Contributing Guide: Learn about our contribution process and coding standards.
- ๐ Report an Issue: Found a bug? Let us know!
- ๐ฌ Start a Discussion: Have ideas or suggestions? We'd love to hear from you.
Released under MIT.