- New: Run Dictate Prompt fully offline with a local OpenAI-compatible server such as Ollama or LM Studio — just set the endpoint and model in Settings. - Chat: email questions now get a real answer instead of dead-ending, replies keep a consistent tone, and the sidebar shows Today and Yesterday expanded by default. - Fix: resolved a Gemini 3 chat error that could break tool calls.

- Improved welcome tour and onboarding flow, featuring a persistent floating window, a unified permissions hub, and reliable system settings integration. - Enhanced chat functionality with image downloads, real-time Google integration (Calendar, Tasks, Gmail), and fixes for streaming freezes and Keychain-related stalls. - Added clearer error handling for non-vision models attempting to read screenshots and overall UI polish.

- Launch at Login is now off by default — enable it yourself in Settings. - Auto-paste is now optional; dictation works without extra permissions. - Clearer setup prompts. - More reliable AI chat with automatic retries on temporary server errors.

- More reliable chat: Fewer freezes during long conversations with generated images; smoother streaming and a more stable message list when sending or resizing the window. - Meeting summaries for every provider: Summaries and titles now work with Gemini, OpenAI, and Grok; missing summaries regenerate when you open the Summary tab. - Smarter transcription & calendar: Your glossary is applied to instructable speech-to-text models; Google Calendar lookups can include past events with normalized dates.

- Generate images in AI Chat with Gemini - ask for a picture or let the assistant use the new image tool. - Chat scrolls more smoothly in long conversations; fixes rare 100% CPU freezes when scrolling. - Read Aloud shows a speaking indicator in the menu bar; retry your last chat message or copy pasted text with your message.

- Fixes chat freezing during long responses — especially when switching chats while a response was still generating. - Up to 10 file attachments per message (previously 5).

• Read Aloud: more reliable text capture; friendly note when nothing is selected • Screenshots save to your folder again, with better permission guidance • Live meeting titles show up in chat sooner • Fixed chat freezing on replies with web sources • Restored menu-bar review prompts

• Read Aloud: pick a voice per provider (Gemini, OpenAI, Grok) in Settings • Chat: /think sets reasoning depth per conversation (all providers) • Read Aloud rewrite sounds more natural with an improved default prompt

Read Aloud: Read selected text aloud, optional AI rephrasing for non-readable content, variable speed. Setup: Record shortcuts by keypress, permissions onboarding, save screenshots and attach in chat. Chat & Meetings: Sidebar with search and meetings area, faster live transcription, more stable meeting titles.

- Paste screenshots and images into Chat; new ⌘3 shortcut captures a region straight to your clipboard. - Updated chat defaults (GPT-5.5, Grok 4.3); Gemini Pro models use deeper reasoning for stronger answers. - Smart Improvement runs more reliably in the background with fewer popups; sharper dictation and chat prompts.

Dictation: Fixed silent drop to idle (especially offline Whisper); clearer “no speech detected” feedback; more forgiving silence threshold. Quality & support: Show logs in Settings; better transcription for large non-WAV files; fewer wasted API calls after Dictate Prompt. Settings: Offline Whisper download confirmation no longer blocks the window; toast stays visible for 10 seconds.

This update improves Dictate Prompt with a stronger default model and stricter language and minimal-edit behavior, shows richer attachment details in chat, and refines slash-command recognition (including /copy).

Trello (OAuth + tools), OpenAI for transcription, chat, and Dictate Prompt, smarter custom transcription API defaults, richer chat UX (copy as Markdown, /copy, command awareness, more screenshots, clearer streaming behavior), Google Tasks/calendar link quality, Grok speed and error clarity, Smart Improvement audio checks and stricter patterns, plus reliability and shutdown improvements.

- Code quality and reliability improvements across core systems

• Reliability: Fixed a rare issue where recording could stay stuck on if you started a new recording immediately after the previous one ended. • Live Meeting: Starting a meeting from a new chat after a previous one ended now attaches the recording to the current session. • Google tools: Calendar and task actions show clearer confirmation details in chat when they succeed. • Gmail: Improved stability when opening large search results. • Google sign-in & Calendar: More robust handling of special characters in tokens, codes, and event IDs. • Settings: “Reset all to defaults” now also clears chat sessions, meeting transcripts, and saved system prompts (API keys and Google tokens remain in Keychain). The confirmation text reflects this accurately.

- Unified chat + live meeting: The chat window (formerly “Open Gemini”) is the main surface; live meeting lives in the same place with session sidebar and related fixes. - Deeper AI + Google in chat: Multi-provider (Gemini + Grok), tool/function calling, Google Calendar/Tasks, read-only Gmail, and many stability fixes. - Streamlined settings: Renamed modes (“Dictate Prompt” etc.), per-mode system prompts, removed old modes (Prompt Read, chat read-aloud), and UI/privacy defaults (e.g. masked API keys, sidebar, pins, chat management).

Gemini model selection: Fixed the model picker not prefilling correctly on the first open after a cold launch.

- Feature Removal: Read Aloud, Prompt & Read, and Improve-from-voice have been removed to focus the app on Speech-to-Text, Speech-to-Prompt, and Gemini Chat. - Gemini Chat Enhancements: Added a prompt queue for sequential processing, prefill from selection with visual chips, and a window toggle shortcut. - Opt-in Controls: Screenshots in Prompt Mode and auto-paste for dictation are now strictly opt-in to improve privacy and reduce permission prompts. - Reliability: Fixed crashes related to main-thread rules and focus-loss bugs, alongside general internal code cleanup.

- Gemini Chat: Attachments, paste handling, markdown tables, session memory (/remember, /context), and in recent releases syntax-highlighted code blocks, LaTeX-style math, and inline images, with steadier layout and window behavior. - Meeting mode: Split window, rolling summary, generated summaries, past meetings in one place, and refinements to controls, titles, and the transcript experience. - Elsewhere: Screenshot context in prompt mode, Whisper glossary and model tuning for dictation/prompt/improvement, a central Stop control, no automatic app termination, optional close-Settings-on-focus-loss, and a fix for heavy disk writes that could get the app terminated by macOS.

- Gemini Chat offers a dedicated window with a global shortcut and persistent sessions as well as slash commands with autocomplete for efficient command execution. - Grounding sources and citations are displayed inline in a FlowLayout and supplemented by an integrated screenshot function for context enrichment.

- Smart Improvement & AI: System prompts now improve automatically based on usage, powered by Gemini for more precise analysis and history management. - User Context & History: Introduction of configurable limits for user context and system prompts, plus tab-specific history for AI generation. - UI/UX & Settings: Optimized prompt editor and direct access to interaction and transcript folders within the app. - Live Meeting & Stability: New safety safeguards for recording duration, consistent timestamps, and improved transcription control, including a cancel shortcut.

- Introduced live meeting recording and transcription, including dedicated settings and direct folder access. - Implementation of a global rate limit with UI notifications for transcription and TTS services. - Optimized TTS workflow and simplified configuration through consolidation of service logic.

Read Aloud and Prompt & Read now support an adjustable playback speed so you can listen faster or slower.

- Introduced conversation history for prompt modes to enable more coherent, context-aware AI interactions. - Enhanced application reliability through optimized TTS processing, updated API endpoints, and improved audio validation. - Added a configurable timeout for transcription history to prevent long-running requests from blocking the app.

- Added configurable recording safeguards to prevent unintended API usage