New

• Screenshots as meeting context — attach screenshots so the AI can read your screen for better summaries (macOS + Windows)

• Rich-text threads — bold, italic, and links, with plain text, markdown, and HTML output

• Idle pill — an optional minimized bar at the screen edge; hover to expand and record

• Paste last dictated text — a shortcut to re-paste your most recent dictation anywhere

• Search threads, dictionary & expansions — filter entries with built-in search

• Speaker label suggestions — autocomplete speaker names from ones you've used before

• Copy part of a command-mode result — select and copy just a sub-section

• Optional timestamps — turn off per-segment timestamps when transcribing a file

Improved

• Streamlined export options for notes and transcriptions in one cleaner modal

• Custom expansions no longer limited by the built-in ones

• Cleaner date separators in the notes list

• Refreshed Cerebras model lineup

• More accurate names in AI enhancement

• Pick which OneDrive account to sync with (Pro)

Fixed

• OpenAI temperature issue when connecting through OpenRouter

• Webhooks now send an application/json content-type

• Transcription error states now clear at the right time

• Stuck modifier keys after system resume

• More reliable local Whisper server recovery

• Local Whisper crashing on the latest NVIDIA GPUs (Blackwell / RTX 50-series)

• Parakeet & Whisper failing to run on pre-2012 CPUs