#145 · Primary category: Speech & Audio
whisper_android
Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android
Project last updated:03/18/26
GitHub Stars
688
Forks
111
Contributors
3
License
MIT
Why we included this project
Android developers who need speech-to-text that works without a network connection will find a working reference here. The repo packages OpenAI's Whisper into TensorFlow Lite and ships two complete apps, one built on the TFLite Java API for easy integration and one on the native API for better performance. A Python script converts Whisper checkpoints into TFLite models, and pre-built APKs let you try the apps before writing any code. The README documents the Whisper and Recorder classes with Java snippets, covering audio capture, transcription, and result callbacks, so you can lift those pieces into your own project. For teams weighing offline ASR on Android, this offers a concrete starting point and a model-conversion path rather than just a demo.
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