Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
sherpa-onnx is an offline speech and audio toolkit built with next-generation Kaldi and ONNX Runtime. Developers use it for speech recognition, speech synthesis, speaker analysis, audio separation and enhancement, voice activity detection, and related tasks across supported devices and programming languages. The catalogue includes an instruction related to using the project.
Latest release v2.0.1 · 26 Oct 2026
1 file for Claude Code: sherpa-onnx CLAUDE.md — 1,119 tokens loaded in every session.
CLAUDE.md A 1,119 tok These files are k2-fsa/sherpa-onnx's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.