BreezeAPP is a mobile AI application developed for both Android and iOS platforms. Users can download it directly from the App Store and enjoy a variety of features offline, including speech-to-text, text-to-speech, text-based chatbot interactions, and image question-answering. Currently, BreezeApp defaults to the Breeze 2 series of models developed by MediaTek Research and we provide simple installation instructions for changing your backend to Llama 3.2 See the Roadmap for additional planned integrations.
This project aims to create a community-driven platform for running AI capabilities locally on Android devices. Our goal is to provide a privacy-focused solution where all AI features work completely offline (airplane mode supported), ensuring your data never leaves your device.
Left: NPU Backend Right: CPU Backend
Speech-to-Text
(In preparation)
Text-to-Speech
- Download the latest APK
- The app includes an in-app model download feature that will automatically prompt you to download required models on first launch.
Looking to build and contribute? Check our Setup Guide for detailed instructions.
-
💬 Text-based chat interface
-
🗣️ Voice input/output support
-
📸 Image understanding capabilities
-
🔄 Multiple backend support:
Model Type Local CPU MediaTek NPU Default LLM ✅ ✅ - VLM 🚧 ❌ - ASR 🚧 ❌ - TTS ✅ ❌ -
/app- Android application source code/docs- Documentation and guides/setup- Installation and configuration guides/architecture- System architecture and design/contributing- Guidelines for contributors/i18n- Internationalized documentation
/assets- Images, videos, and other static resources
Contributions are welcome! See our Contributing Guide to get started.
The license for this project is pending determination - see the LICENSE file for details.
- Executorch for LLM/VLM framework
- k2-fsa/sherpa-onnx for ASR/TTS capabilities
- MediaTek Research for core AI engines
MediaTek Research, a memeber of the AI Alliance.
Contact us: info@mtkresearch.com