#85 · Primary category: Speech & Audio
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.
Project last updated:08/26/26
GitHub Stars
1.5K
Forks
139
Contributors
14
License
MIT
Why we included this project
For people who type all day but would rather talk, Amical is a desktop dictation app that runs Whisper locally and drops the transcript straight into whatever window you have focused, be it an editor, a chat message, or an email draft. Because the model lives on your own machine, transcription works fully offline once set up, which suits anyone who values privacy or regularly works without a reliable connection. On top of the raw dictation it adds light processing through open source LLMs, including language detection and formatting. Teams and individuals looking for a self-hosted note-taking tool will appreciate that their audio and text never have to leave their hardware.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production