Speech Note
An offline speech-to-text and text-to-speech app for Linux and Sailfish OS, with local translation, voice typing and MPL-2.0 open-source licensing.
Speech Note combines offline dictation, reading aloud and translation in a desktop app for Linux and Sailfish OS. It's for people who want to take multilingual notes, type by voice or listen to text without sending their words to a cloud service. Speech and text processing stay on your device; models are downloaded separately through the app's graphical browser.
You can dictate into the active desktop window or copy recognized text to the clipboard. Global keyboard shortcuts let you start listening or reading while the app is in the background. On Wayland, voice typing needs ydotool, and global shortcuts depend on desktop support.
For audio work, Speech Note can produce SRT subtitles and read subtitle files aloud in time with their timestamps. It can adjust speech speed to fit each subtitle segment, so you can create a timed voice-over. You can also save generated speech as an audio file.
Its choice of engines includes whisper.cpp, Parakeet, Faster Whisper and Vosk for speech recognition. Voice synthesis options include Piper, Kokoro, RHVoice and F5-TTS; Bergamot handles translation. Language coverage depends on the engine, and the app accepts compatible custom models.
Speech Note is open source under the Mozilla Public License 2.0 and is available for Linux as a Flatpak. Optional NVIDIA and AMD GPU acceleration can speed up supported operations. Faster Whisper, Coqui TTS and Mimic 3 are available only on x86-64.
