Install murmure

About murmure

Fully local, private and cross platform Speech-to-Text with LLM Post-processing

What's new in 1.10.1

Murmure 1.10.1 A big update on Murmure's core features, with a strong focus on speed, accuracy, and a smarter dictionary. Faster Murmure now splits your recording on natural pauses and transcribes each part in the background while you keep talking, so long dictations finish much faster and the old 5 minute limit is gone. More accurate A brand new AI model (thanks @thiswillbeyourgithub) brings noticeably better accuracy and far fewer unwanted switches to English. It works together with a reworked audio pipeline that prepares your voice with higher quality resampling before it reaches the model, which also helps a lot on low-end microphones. Smarter dictionary The dictionary has been redesigned around a completely new approach. Your custom words are now boosted directly inside the model's decoding, so they get recognised far more reliably than before. Also new - A new murmure command to transcribe audio files from the terminal. - UI improvements across the app, plus monochrome tray icons on Linux and macOS. - A close button on the overlay to cancel an ongoing transcription. Fixes - Smoother recordings on Linux, no more crackling on some setups. - macOS click-through and cancel button now work correctly. - Bluetooth headsets no longer stay active between recordings. - Several shortcut fixes, including duplicates and Ctrl only shortcuts. - Security updates for dependencies. 🙏 Thanks - Beta testers, @HachetAmaury, Walden, CollectifWeb - Contributors, @thiswillbeyourgithub - Donors, Ubertartine, Chase, Gizmo38, Aparrot, Raphael, Stephen Berard, B0g, AndraaX, Prometee, scwall, tho...

Read release notes

Version history