All tasks / Tools
sherpa-onnx
Offline speech toolkit running ASR, TTS, VAD and diarization models via ONNX on desktops, phones and embedded boards.
- k2-fsa (Next-gen Kaldi)
- Local only
- Free, open source
Where it ranks
- CText to speechLocal servers & APIs · Local · via Kokoro-82M v1.0
- ATranscriptionEngines & APIs · Local · via Whisper large-v3
Tools without a benchmark of their own inherit the tier of the best model they offer.
Facts
- Vendor
- k2-fsa (Next-gen Kaldi)
- Approach
- Local servers & APIs, Engines & APIs
- Where it runs
- Runs only on your own hardware
- Interface
- API, Command line
- Skill level
- Advanced: command line, node graphs or self-hosting
- Price
- Free, open source
- Pricing notes
- Free and open source.
- Source code
- Open source (Apache-2.0)
- GitHub stars
- 15.4k (19 Oct 2026)
- Last verified
- 19 Oct 2026
Price from github.com, 19 Oct 2026.
Models it gives you
- AWhisper large-v3OpenAI · open weights
- BParakeet TDT 0.6B v3NVIDIA · open weights
- CKokoro-82M v1.0hexgrad · open weights