{"id":50903,"date":"2026-04-07T13:29:12","date_gmt":"2026-04-07T13:29:12","guid":{"rendered":"https:\/\/ubuntuhandbook.org\/?p=50903"},"modified":"2026-04-07T13:29:12","modified_gmt":"2026-04-07T13:29:12","slug":"speed-of-sound-new-voice-typing-app-for-linux-desktop","status":"publish","type":"post","link":"https:\/\/ubuntuhandbook.org\/index.php\/2026\/04\/speed-of-sound-new-voice-typing-app-for-linux-desktop\/","title":{"rendered":"Speed of Sound – New Voice Typing App for Linux Desktop"},"content":{"rendered":"

\"\"<\/p>\n

Looking a way to automatically type text on your PC by speaking? Here’s a new app to do the job in Linux desktop!<\/p>\n

It’s Speed of Sound<\/a>, a free open-source tool that uses local AI model to convert your speech to text and write anywhere that’s currently in focus.<\/p>\n

<\/p>\n

The app comes with a Whisper Tiny model (made by OpenAI). Just press a key to start recording, speak your text, stop recording, then it will use the model to convert the speech to text, and automatically type into any focused application.<\/p>\n

\nhttps:\/\/ubuntuhandbook.org\/wp-content\/uploads\/2026\/04\/speedofsound.mp4<\/a><\/video><\/div>\n

The whole process works offline on user’s computer<\/b>. Though, it supports downloading more voice models, connecting to cloud services such as Anthropic, Google, or OpenAI, or using self-hosted Ollama, vLLM or llama.cpp services on your local server that require network permission.<\/p>\n

\"\"<\/p>\n

It supports multiple languages<\/b>. You can set the primary and secondary languages, then switch between them on the fly.<\/p>\n

As non-native speaker, it can accurately type out what I said in English. Though, probably due to language model, it somehow does not work as expected when speaking in my native language.<\/p>\n

\"\"<\/p>\n

How to Install Speed of Sound<\/h3>\n

The app works on both X11 and Wayland<\/strong>, and it’s available to install in different package formats, choose any one of them that you prefer:<\/p>\n