forked from TypeWhisper/typewhisper-win
-
Notifications
You must be signed in to change notification settings - Fork 1
GPU and CUDA
Chris Smashe edited this page Jun 17, 2026
·
4 revisions
TypeWhisper ships an optional CUDA backend that runs the bundled whisper.cpp transcription engine on a compatible NVIDIA GPU. This page covers what it requires and what it currently applies to.
To use the CUDA backend you need:
- An NVIDIA GPU and driver.
- CUDA 12 runtime/toolkit libraries providing
libcudart.so.12andlibcublas.so.12.
If those libraries are missing, the Linux UI disables the relevant control and explains what's needed — see Troubleshooting.
CUDA currently applies to the bundled whisper.cpp engine. Other bundled local engines stay on CPU.
- Transcription engines — the engines available, including bundled whisper.cpp.
- Requirements — full list of Linux requirements and optional helpers.
| Date | Change |
|---|---|
| 2026-06-17 | Initial version. |
Home · Repository · Issues · Releases · GPLv3
TypeWhisper for Linux is a community Linux port. Each page lists its own change history in the Changelog section above.
Getting Started
Using TypeWhisper
- Dashboard
- Dictation
- Global Hotkeys
- Text Insertion
- File Transcription
- Recorder
- History
- Dictionary & Term Packs
- Snippets
- Profiles
- Prompts & AI Actions
- Text Cleanup & Formatting
- Long-term Memory
Settings
Plugins
Automation
Platform & Troubleshooting
Project