Speed of Sound

Overview

Speed of Sound is a speech-to-text program, available on Linux.

Features described in its Flathub listing, in its GitHub repository and on its official website: voice input and commands, self-hosting on your own server, local model execution, open-weight models (Llama, Mistral…).

Services and protocols mentioned: Ollama.

Overview written by LicitPro from the documentation published by the authors and the cited sources; we have not tried the resource ourselves.

At a glance

Speed of Sound is completely free: it is open source software, and every feature is available without paying or subscribing.

Its licence (MIT) is a permissive open source licence: use, modification and redistribution are allowed, including in commercial projects.

About

Speed of Sound is a voice-typing app for the Linux desktop. By default, transcription runs entirely on-device, so no audio ever leaves your machine. The app ships with a built-in multilingual Whisper model and supports additional models from the Whisper, Parakeet, and Canary families to improve accuracy. Offline, private transcription with popular open speech models (Whisper, Parakeet, Canary) Multiple activation options: click the in-app button or use a global keyboard shortcut Types directly into any app via XDG Desktop Portals (supports X11 and Wayland) Optional text polishing with LLMs, supports self-hosted services like Ollama, vLLM, and llama.cpp Optional cloud providers supported for resource-constrained hardware environments Please visit speedofsound.io/getting-started after installation.

Description from Flathub — AppStream (Flathub)