#137 · Primary category: Speech & Audio
whisper-writer
💬📝 A small dictation app using OpenAI's Whisper speech recognition model.
Project last updated:08/24/24
GitHub Stars
1.1K
Forks
196
Contributors
8
License
GPL-3.0
Why we included this project
WhisperWriter is a small dictation app that turns a single hotkey into a full speech-to-text pipeline. By default, pressing ctrl+shift+space starts recording from your microphone, and the transcribed text lands directly in the active window, so it works with any app you're typing into. Four recording modes let you choose between continuous listening, stopping after a pause, toggling with the hotkey, or holding the key to record, which covers most hands-free workflows. Transcription can run entirely offline through faster-whisper or hit the OpenAI API when you'd rather offload the compute. A small status window shows the current stage, and all settings live in a GUI rather than a config file. For developers, the codebase is also a straightforward example of wiring Whisper into a PyQt5 desktop application.
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