Whisper models in Superwhisper are free without Pro
The October 31 reminder covers local Whisper models for everyone, though it does not include cloud models or other Pro tools.
Every SuperWhisper update in one feed — release notes, features and changes, straight from the source.
23 updates
The October 31 reminder covers local Whisper models for everyone, though it does not include cloud models or other Pro tools.
The post and its image name a new keyboard, swipe typing, Liquid Glass, and iPhone Duo, though they name no price or plan.
The Android post shows a control you can drag, dock, and tap. The docs call it a floating bubble and limit the app to phones.
Superwhisper 3.1.0 localizes the interface in Japanese, records FaceTime calls in Meetings, and renames the Modes tab to Transcribe.
Version 3.0.2 listed a Grok Bot meetings agent on October 20, and Superwhisper's October 27 post says you can talk to Grok Bot about your meetings.
Version 3.0.2 speeds up Cohere Transcribe, adds a Grok Bot meetings agent, and fixes crashes on Intel Macs and in History.
The new Meetings feature handles recording, transcripts and summaries automatically, with a choice of cloud or local processing.
Version 3.0.0 adds speaker-labelled transcripts and summaries, using cloud or local models, in a tab separate from dictation history.
Version 3.0.1 adds a glass toolbar, a steadier live meeting card and a Cmd-W confirmation to the Meetings window.
Version 2.19.3 also retries dropped pastes in Chromium browsers and fixes paste formatting in Signal Desktop and other Electron apps.
The fix is included in version 2.19.2, released on October 5, 2026.
The fix is included in SuperWhisper 2.19.1, released on October 5, 2026.
Version 2.19.0 adds a Muffle option for other apps' audio and makes Lower playback scale to 30% of your current volume.
SuperWhisper 2.18.5 improves filler word removal in Scribe realtime and fixes audio dropouts, a History CPU spike and CSV vocabulary import.
Superwhisper 2.18.4 makes BYOK setups follow org-wide cloud model settings and improves S1-mini transcription on longer recordings.
Silence removal is now enabled by default for cleaner transcriptions. You can turn it off in Sound settings.
All local Whisper models are now free on macOS, giving you high-quality voice to text at no cost. Agent plugin support for DeepSeek Harness.
Updated default modes and models for a smoother onboarding experience. Improved S1-mini stability on Intel-based Macs. 2.18.0
Added S1-mini, an on-device language model with tone control, that cleans up and formats your dictated text without a network request.
Added tone control when using Message, Mail, and Notes, giving you more say over how your text sounds.
Introducing the S1 family of models. Improvements Faster, smoother settings window with refined picker, disclosure, and Appearance card animations.
Automatic language detection for Cohere Transcribe Refreshed the app icon The app name is now capitalized to match updated branding. 2.17.0
The engine streams text as you speak and supports 90+ mixed languages, free on Mac, Windows and iOS.