sherpa-onnx
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 scores 7.1/10 (Strong) in Voice & Realtime.
Language C++ License Apache-2.0 Stars 13.4k★ Type library Self-host Yes Repo k2-fsa/sherpa-onnx Homepage https://k2-fsa.github.io/sherpa/onnx/
Quality
Strong 7.1
Adoption 53
Activity 75
Maturity 99
Community 55
Capability 50
Show the math
Overall 7.1/10
value = 7.1/10
score = value
Adoption 5.8/10
value = 53.1/100
score = 1 + 9 * value / 100
Activity 7.7/10
value = 74.5/100
score = 1 + 9 * value / 100
Maturity 9.9/10
value = 99.4/100
score = 1 + 9 * value / 100
Community 6/10
value = 55.4/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
13.4k★ GitHub stars
109/90d Recent commits
22 devs/90d Recent contributors
3.8y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
stt tts vad offline cross-platform