#115 · Primary category： Speech & Audio
sherpa-ncnn
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.
Project last updated：10/20/25
GitHub Stars
1.8K
Forks
218
Contributors
21
License
Apache-2.0
Why we included this project
Sherpa-ncnn runs streaming speech recognition, text-to-speech, and voice activity detection entirely on the device, so a voice assistant or transcription tool can work with no internet connection. Everything sits on Tencent's lightweight ncnn runtime rather than a heavier inference framework, and the same code compiles for iOS, Android, Windows, macOS, Linux, and WebAssembly, plus ARM and RISC-V boards like the Raspberry Pi and VisionFive2. Bindings for C++, Python, Go, C#, Kotlin, JavaScript, and Swift mean most teams can call it from the stack they already use. If speech features have to work reliably in constrained or privacy-sensitive environments, this is a practical way to get them there.
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