What it does
sherpa-onnx is a toolkit for working with speech without an internet connection. It can turn speech into text, read text aloud, tell who is speaking and when, detect when someone is talking, spot keywords, identify the language spoken, add punctuation and clean up noisy audio.
It runs on a wide range of devices, including Windows, Mac, Linux, Android and iPhone, small boards like the Raspberry Pi, and specialised AI chips. Developers can use it from a dozen programming languages, and there are some ready-made demo apps.
Who it's for
Developers adding private, offline voice features to apps and devices.
Can I use it without coding?
Developers only. It's a developer toolkit, though some pre-built demo apps are available. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Windows, Linux, Phone, Web browser
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Try it in your browser on its Hugging Face demo pages, with nothing to install.
- Or download a ready-made demo app from the project's GitHub releases page.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe