openwhispr

OpenWhispr 1.10.4

Tone & Style writes your dictation, and the assistant's drafts, in the tone you pick for each kind of app. The AI Summary is more detailed by default, notes can link to a calendar event, and you can set a reasoning effort per model scope.

🌟 Highlights

• 🎨 Tone & Style — Pick a tone for personal messages, work chats, email and everything else, and cleanup writes in it for the app you're in. Off by default; turn it on in Settings → Tone & Style.
• 📝 Detailed AI Summary — Generate AI Summary now writes the same notes as the Detailed Notes template.
• 📅 Calendar events on notes — Link any note to its meeting to pull in the guests and join link.
• 🧠 Reasoning effort — Choose how hard reasoning models think, per scope.
• ❓ Ask about OpenWhispr — The chat answers questions about the app from the docs and your settings.

✨ Also new

"This is me" in the speaker picker, searchable overflow for long sidebar folders, onboarding key checks as you type, Claude 5.5 models, and Qwen3.8 27B on Groq.

🛠 Fixes

• Dictation: Local and self-hosted cleanup models always run when you dictate through OpenWhispr Cloud or a streaming provider, and a failed selection edit keeps your transcript.
• Meetings and notes: Resumed recordings keep speakers apart, stopping a local meeting keeps its last words, and in-person speakers are no longer all attributed to you.
• Transcription and AI: OpenAI live dictation uses your language and dictionary, stalled replies no longer hang, and self-hosted models stay selected after a restart.
• Linux: Voice assistant answers paste at the caret, and paste works on niri, sway, Hyprland and KDE with non-Latin layouts.
• Windows: Local Whisper works for user profiles with accented names.

⚠️ Heads-up

On niri, sway and Hyprland, auto-paste into Wayland apps now needs wl-clipboard.

Full details in the changelog.

🙏 Thanks

Thanks to @Chadpiha, @boseq, @greatcoat, @hsusul, @IdrisGit, @clarkmaan, @Nathan-Roll1, @Adityakk9031, @etzelm, @widechaos, @Jrjy3, @jay-tau, @agn-7, @matthias-vera, @Abhishek-B-R, @atty57, @ivaschru, @isacgalvao, @tishmen, @Li-john1021 and @Sevi-py, and to @PalaceChan and @mhasgari for their bug reports. 🎉

Prebuilt Linux text monitor binary for auto-learn correction monitoring.

This binary uses AT-SPI2 to detect text field changes after paste.

OpenWhispr 1.10.3

The assistant can now act in other apps: it drafts and sends email, posts to Slack, and works with Linear and GitHub issues, always behind a card you approve. Notes get templates for the AI Summary, actions that answer in a docked chat, and real tables. OpenWhispr also uses far less memory when idle, shows a plain-language error when your API key or provider fails, and fixes a long list of bugs on Linux, Windows and macOS.

🌟 Highlights

• 🔌 Connectors — The assistant can draft and send email (Gmail), post to Slack, and work with Linear and GitHub issues. Nothing goes out until you press Send on a card showing exactly what will be sent. Paid plans; connect in Settings → Integrations. (#2331, #2369, #2385, #2401, #2402)
• 📝 Note templates and actions — Templates shape the AI Summary, and actions like Follow-up email answer in a chat docked beside the note instead of overwriting your summary. (#2397, #2557, #2578, #2598)
• 📊 Tables in notes — Tables stay tables when you edit a note, and a formatting toolbar appears when you select text. (#2255)
• 🪶 Lighter when idle — Search and meeting detection only run when needed, cutting idle memory use from about 500 MB. (#2299, #2371)
• 💬 Clear error messages — When your own API key or provider fails, you get a plain-language message with a link to fix it. (#2510)

✨ Also new

Echo cancellation for meetings, an option to keep the local model loaded, a folder picker in the meeting notification, dictation audio that survives a crash, a macOS permission helper in onboarding, Apple sign-in on Windows and Linux, and live speaker names on Linux.

🛠 Fixes

• Windows: Teams meetings record everyone for the whole call again. (#2233)
• Transcription: API key changes apply without a restart, and AssemblyAI, Corti and Gemini Live no longer drop words.
• Assistant: Answers paste as plain text, follow-ups don't repeat actions already sent, and images in replies are no longer loaded automatically.
• Linux: GPU rendering is back (except on NVIDIA), Settings no longer lags, and paste waits for you to release held keys.
• Notes and meetings: Assistant edits to a note can be undone and never wipe fields by accident, clearing a note now syncs, and fixes for Join & transcribe, live transcripts on reload, and TXT export. (#2602, #2604)

⚠️ Heads-up

The Windows portable .exe is discontinued. Use the installer instead. (#2301)

The full list is in the changelog.

🙏 Thanks

Thanks to @Chadpiha, @boseq, @greatcoat, @hsusul, @IdrisGit, @clarkmaan, @Nathan-Roll1, @gabrielste1n, @sochotnicky, @kuleje, @TrackerGit, @zhongwater123, @emanuelet, @marselsel, @folks-samuel-cb, @STiFLeR7, @Adityakk9031, @stantheman0128, @cadufpolis, @Abhishek-B-R, @dajiaohuang and @hiro-nikaitou for their work on this release. 🎉

And thanks to @jaszczurovsky, @TaiFeng, @jsholcomb, @wadamek65, @KishenG and @amarpreet2209 for reporting and narrowing down the Teams capture bug (#1265).

Prebuilt Windows system audio helper binary for meeting transcription.

Captures system audio via WASAPI process loopback (exclude mode), hearing every application on every output device while excluding OpenWhispr's own audio. Requires Windows 10 2004 or later; older systems automatically fall back to Chromium display-media loopback.