This update adds screen recording with a video player in transcript, plus inline screenshots with timestamps right in your transcripts. Summit now recognizes known speakers live as you record, and you can send action items to Apple Reminders with assignees pre-filled from your meeting. Folders are more powerful: create subfolders, drag to reorganize, and manage them from a dedicated sidebar section. New document list view modes (Default, Comfortable, Compact) let you choose your layout, and document chats now live in the main Chat menu. Recording auto-stop now works for manual recordings and stops when your meeting app releases the mic. You can skip summarization on low battery, assign default folders to calendar events. We added OpenRouter support and more on-device AI models. Plus many fixes: alerts when the mic captures no audio, safer storage folder handling, more reliable model downloads, clearer summarization errors, and better search and live transcription.

Summit 1.9 brings powerful new ways to capture and share your meetings. You can now email a meeting summary directly from the app, control recordings from the menu bar without opening Summit, import existing audio files, and attach files and capture screenshots to any recording. Chat now streams responses in real time and can be scoped to the documents you select. Auto-record got smarter: aware of tentative calendar events, attendee response status, and an option to detach events from recordings. Local AI models are now recommended based on your Mac, and AI models download faster with download progress in the toolbar. Summaries are more accurate, using each recording's actual date and precise timestamps for insights and action items. Action items assigned to a person now show up on their profile. This release also fixes calendar events not updating automatically, notes occasionally losing text, recording duration mismatches, key insights losing their order, and other reliability improvements.

Notes now render as formatted markdown with a quick Edit/Save toggle. Added new Gemma 4, Qwen 3.6 and Qwen 3.5 local models, plus a 24GB RAM category to help you pick the right model for your Mac. Active subscribers can now upgrade to yearly or lifetime plans from settings. Category cards are clearer, with a green spectrum for models that fit your hardware and an orange Try badge for stretch picks. Fixed calendar auto-record not disabling when the mode is turned off, and corrected meeting prep counts.

- Calendar event view UX improvements - Fixed Whisper regression

Summit 1.8.2 brings per-recording language selection, you can now override the transcription language for individual recordings. You can also report unhelpful AI summaries directly from the document. This update also improves speaker recognition accuracy across recordings, sharpens recurring meeting detection in meeting prep, and raises the number of search results shown when using combined filters. Document titles now automatically include the associated calendar event name. Bug fixes: - notes no longer disappear while recording a document - weekday labels in the date filter calendar are correctly aligned.

New Features - Copy button on insights header for quick sharing of AI-generated insights Improvements - Show first insight instead of transcript preview in sidebar for more useful at-a-glance summaries - Folders now sorted alphabetically in the Move to Folder dialog - Improved call detection snooze behavior — resets properly on new microphone sessions Bug Fixes - Fixed calendar events disappearing from home page after a sync failure - Fixed calendar week view event positioning alignment - Fixed mic/speaker audio track misalignment during silence gaps - Fixed recording state being lost when the window is closed and reopened

This update brings deep links so you can open Summit documents directly from other apps like Obsidian. You can now import video files with automatic audio extraction, choose your preferred microphone with smart fallback, and move documents between folders with drag-and-drop. New AI improvements include an insight validation step that reduces hallucinations in summaries, smart processing delays for back-to-back meetings, and feedback when no speech is detected in a recording. Speaker diarization is now optional, and you can search templates in the picker. Other additions: audio storage management with size counter and bulk delete, status bar icon can be hidden, Cmd+F to focus search, alphabetically sorted folders, accessibility font size support, and speaker merge undo. Bug fixes: resolved iCloud-related database corruption, fixed in-app purchases blocked by biometric dialogs, fixed sleep/wake deadlocks, fixed cursor jumping after @mentions, and numerous other stability improvements.

Summit AI Notes 1.7 NEW FEATURES Full localization support for German, Spanish, and Russian. Bookmarks & AI Insights: Add bookmarks during recordings and convert them to AI-generated insights with context. Navigate directly to any moment using timestamps. Meeting Prep: Get AI-powered preparation notes for upcoming meetings right on your Home page. Calendar Week View: See your week at a glance with actual calendar colors and side-by-side concurrent events. DeepSeek Support: Use DeepSeek as your cloud AI provider. Auto-Export: Automatically save meeting notes as markdown files. Silence Trimming: Recordings automatically trim trailing silence. IMPROVEMENTS Redesigned recording controls with audio level indicators and compact status bar. Better speaker management in transcriptions. Copy insights and action items to clipboard from the menu. Smarter rate limit handling for cloud AI. BUG FIXES Fixed crashes from Metal race conditions. Fixed auto-record for future calendar events. Fixed audio source reset on new recordings. Fixed calendar time indicator issues.

- This update brings calendar integration with auto-record scheduling for your meetings! - Chats became multi-document, which lets you ask questions across all your notes at once. - New AI enhancements generate insights and action items from your recordings. - You can now filter transcriptions by speaker, control playback speed, and choose from summarization templates. - Mistral 3 models are now supported. We've improved folder navigation, added echo deduplication for clearer transcriptions, and updated our AI libraries for better performance. Bug fixes include better handling of silent recordings, more reliable audio preprocessing, automatic cleanup of processed audio files, and improved USB audio device detection for call recording.

Local chat with documents! - dive deep into the transcript, chatting with the document, local and secure! AI Transcript Cleanup - Automatically remove filler words and irrelevant segments from your transcripts using AI. Summarization Templates - Create reusable templates for different meeting types with folder and document-level overrides. Enhanced Export - Merge audio tracks into a single file, export as ZIP archives, and see real speaker names in markdown. Redesigned Recording - Large sidebar record button with live timer during recording. Plus: Bug fixes for audio mute state, OpenAI support, and improved tag extraction.

Transcription & Audio - Re-transcribe Segments - Right-click any conversation bubble to re-transcribe just that segment or from that point to the end. Perfect for fixing hallucinations or poor quality transcriptions without re-processing the entire recording. - Click to Seek - Click conversation bubbles to jump directly to that position in the audio playback. Makes it easy to hear exactly what was said. - Delete Conversation Bubbles - Remove individual transcription segments with a right-click context menu option. - Auto-Stop Recording on Sleep - Recordings now automatically stop and finalize when your Mac goes to sleep, preventing data loss. AI & LLM Integration - Full Anthropic (Claude) Support - Complete integration with Anthropic's Claude API as an alternative to OpenAI, Google Gemini, or local models. - Rename Placeholder Participants - AI-generated content now automatically replaces placeholder speaker names (like "Participant-abc123") with actual speaker names when you rename speakers. User Interface - Folder Icons in Sidebar - Visual folder icons now appear in the document sidebar for better organization. - Fluent Audio Model Download Progress - Visual progress indicators when downloading new transcription models. - Explicit Permissions Check - Clearer permission request flow with streamlined UX. - In-App Update Checker - Automatic checking for new app versions with notifications. Organization & Management - Delete Tags and Speakers - Clean up unused tags and speakers directly from the UI. - Speaker Merge Feature - Merge duplicate speaker profiles into a single identity. Bug Fixes - Fixed FluidAudio Confidence Data - Corrected confidence score handling for FluidAudio transcription model. - Preserve User Titles - User-edited document titles are now preserved when re-running summarization. - Rename Untitled Documents - Title field correctly maintained for documents without custom titles. - Performance & Stability improvements

Bug fixes

New Features - Speaker identification - Automatically detect and label different speakers in your transcriptions (requires re-transcribing existing documents) - New Transcription Engine - New transcription engine available in settings for improved accuracy - Folders - Organize your documents into folders for better management - Action Items - View and manage all action items in a centralized page - Import Audio - Import and transcribe audio files directly into Summit AI Notes New Models - GPT-OSS-20b - The most powerful AI model to date, delivering the best results in testing - Granite 4.0 Micro - Two new models from IBM for enhanced transcription capabilities

- Search through transcriptions - Edit transcriptions - Added Large transcription models - Recommend transcription model base on available memory - Delete Audio files - Fixed Custom folders - Fixed Search widget - When using Custom Cloud Provider the model name input stays visible since Anthropic doesn't support the models endpoint - Voice activity detection model will be downloaded automatically if missing