Speed of Sound

#Voice #typing for the #Linux desktop:

Features
Offline, on-device transcription powered by Whisper, Parakeet, Canary, and more. No data leaves your machine.
Multiple activation options: click the in-app button or use a global keyboard shortcut.
Types the result directly into any focused application using Portals for wide desktop support (X11, Wayland).
Multi-language support with switchable primary and secondary languages on the fly.
Works out of the box with a built-in multilingual Whisper model. Download additional models from within the app to improve accuracy and language coverage.
Optional text polishing with LLMs (Anthropic, Google, OpenAI), with support for a custom context and vocabulary.
Supports self-hosted services like vLLM, Ollama, and llama.cpp (cloud services supported but not required).

Getting Started
The easiest and recommended way to install Speed of Sound is from Flathub or from the Snap Store. Alternatively, AppImage, Deb, and RPM packages are also available from the releases page.
For initial configuration, troubleshooting, and other resources, visit speedofsound.io

#stt