Built in C++, sherpa-onnx is an open-source speech and audio tool maintained by k2-fsa. The repository has collected 15k stars and 1.8k forks; the latest push was in October 2026. Docs and downloads are linked from k2-fsa.github.io.
“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”
— k2-fsa, project description on GitHub
Details
| Category | Speech & Audio |
|---|---|
| GitHub stars | 15,357 |
| Forks | 1,791 |
| Language | C++ |
| License | Apache-2.0 |
| Last updated | |
| Owner | k2-fsa |
| Website | k2-fsa.github.io/sherpa/onnx/index.html |
| Repository | k2-fsa/sherpa-onnx |
Tags
aarch64androidarm32asrcppcsharpdotnetios
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.