Welcome. This is the GitHub home for VocaHQ: free, open-source speech-to-text across the machines you already own.
Speak, and the words land in the field you were already using. After a speech-to-text model is downloaded, on-device mode keeps audio and processing on that machine, locally. If you want shared or larger compute, you can point a client at a VocaGateway you self-host yourself. There is no Voca account. No credit cards. Just setup and go.
Using the tools? Pick your platform below. Want to help build them? You are already in the right place.
| Platform | Project | Repo | Site | Status |
|---|---|---|---|---|
| Linux | VocaLinux | VocaHQ/vocalinux | vocalinux.com | Available now |
| macOS | VocaMac | VocaHQ/vocamac | vocamac.com | Beta |
| Windows | VocaWin | VocaHQ/vocawin | vocawin.com | Beta |
| iOS / Android | VocaPhone | VocaHQ/vocaphone | vocaphone.vocahq.com | Android beta / iOS TestFlight |
| Gateway | VocaGateway | VocaHQ/vocagateway | vocagateway.vocahq.com | Beta |
You do not need to know the whole family. Start with the platform you actually use.
- Join Discord and say hello
- File an issue when something breaks, or when a README skips a step you needed
- Open a PR. Code, tests, packaging, and clearer docs all count
- Try a beta, including unsigned VocaWin, and tell us what failed
Issues and PRs are welcome on every project.
Thanks for starring, filing issues, contributing, and using these tools.
To infinity and beyond!
Came here from an old personal-account link?
If you followed an old jatinkrmalik/... GitHub link, you are in the right place. Those URLs redirect here.