Release history

What's new in AnyBrief

New features, improvements and important fixes. Every published download is Developer ID signed and notarized by Apple.

Nemotron 3 speaker diarization

New

  • Whisper settings now offer Nemotron 3 for local speaker diarization on Apple Silicon Macs.
  • Download the model from settings with SHA-256 verification; speaker counting is automatic.

Improvements

  • Meeting technical details preserve the diarization engine and parameters used during transcription.
  • Whisper continues to use FluidAudio on Intel Macs, where Nemotron selection is unavailable.

Less background work while the window is open

Fixes

  • Processing stages and LLM progress now update from events without frequent full Dashboard polling.
  • Recording elapsed time and the countdown to automatic stop update every second.
  • Unchanged data no longer triggers unnecessary interface redraws.

Recovery for interrupted recordings

Fixes

  • After an unexpected app exit, recordings with readable audio files resume processing automatically.
  • If stopping a recording reports an error but the audio files were saved, processing continues with a warning.

More resilient audio device switching

Fixes

  • Recording handles microphone and system audio route changes more reliably during a meeting.
  • Recorder health checks allow brief interruptions while an audio device changes.

A more responsive recording interface

Fixes

  • Muting and resuming the microphone now updates the button and level indicator immediately.
  • Starting and stopping a recording updates the workspace state without waiting for polling.
  • Log reading and meeting folder deletion or renaming no longer block the interface with file operations.
  • System permission buttons show progress and prevent duplicate requests.

More reliable AirPods recording

Fixes

  • Recording no longer aborts when AirPods or another Bluetooth microphone changes its audio format during startup.
  • AnyBrief waits for the Bluetooth route to stabilize and retries microphone capture automatically.
  • Selecting the microphone that is already the system input no longer causes an unnecessary device reconnection.

Improvements

  • Website links are now available in the About window and Diagnostics menu.
  • Calendar rows are cleaner, and the appearance and language controls align with the other settings.

A new workspace for your meetings

New

  • Import meetings from audio or video with a title and date.
  • New meeting workspace with search, a resizable list and Summary, Transcript, Audio and Technical details tabs.
  • Start a new recording while a previous meeting is processing, with separate sidebar entries.
  • Light, dark and system appearance.
  • Contextual setup hints and a readiness check in Diagnostics.

Improvements

  • Separate settings tabs for microphone, transcription, LLM, calendar, windows and API.
  • Listen to system audio and microphone separately, copy technical details and rename an active recording.
  • More compact lists and forms, plus default window rules for common calling apps.
  • Improved handling of silent recordings, processing errors and missing summaries; fixed a crash when switching LLM connections.
  • Update checks report through notifications. Added feedback and CLI setup links.

Smaller recordings and more flexible exports

New

  • Export rules can now save the summary, the transcript, or both documents.
  • Filename templates support a new {type} variable that expands to summary or transcript.
  • The meetings list now includes an action to reveal exported files in Finder.

Improvements

  • Raw meeting audio is now compressed to MP3 even when summarization is not configured or does not complete, significantly reducing storage use.
  • The local meeting recording remains the source of truth, so transcription and summarization can still be repeated as before.

More reliable diarization and cleaner Whisper output

New

  • FluidAudio offline diarization now uses the full OfflineDiarizerManager pipeline.
  • Speaker count supports either an exact value or an upper bound; calendar automation uses the maximum expected participant count.
  • FluidAudio and whisper.cpp now have separate recognition dictionaries that follow the selected STT provider.

Improvements

  • Whisper now uses Silero VAD to remove silence before recognition, suppressing invented phrases and subtitle-credit hallucinations.
  • Original word and speaker-turn timestamps are restored correctly after VAD processing.
  • Diarization models now have a dedicated preparation command instead of processing a silent WAV.
  • The recognition dictionary now sits with the selected STT options, and the provider selector is larger and clearer.

More accurate recognition and clearer processing

New

  • The shared recognition dictionary is now passed to FluidAudio and whisper.cpp, with preferred spellings and known variants.
  • Speaker separation can be disabled for faster recognition without diarization.
  • Meeting actions now include Repeat Transcription and Repeat All.

Improvements

  • FluidAudio recognizes the full recording in one pass and aligns timestamped words with speaker turns, preserving context across long meetings.
  • A fixed speaker count now constrains diarization output, and the default speaker sensitivity is now 0.65.
  • Repeat transcription now converts archived MP3 tracks to temporary 16 kHz mono WAV before FluidAudio or whisper.cpp runs, preventing MP3 decoder errors and hallucinations.
  • Recognition logs now report the actual provider, model, and language instead of placeholder values.
  • Processing status now shows transcript cleanup, the active LLM connection, and fallback transitions.
  • Before launching Codex or Claude, the app quickly checks its API and immediately falls back to the next LLM when the service is blocked or unavailable.
  • CLI providers now use only the connection's overall timeout, so long generations without intermediate output are no longer stopped after 120 seconds.
  • Microphone, speaker separation, and recognition dictionary settings now use compact collapsible cards.
  • The provider selector and whisper.cpp options now follow one consistent grid, with larger controls and tighter grouping.
  • Russian and English localization has been reviewed and completed.

Whisper.cpp and transparent transcription diagnostics

New

  • A second transcription provider: local whisper.cpp recognition combined with FluidAudio speaker diarization.
  • Choose between tiny, base, small, medium and large-v3-turbo-q5_0 Whisper models, plus a specific recognition language or automatic detection.
  • Metal acceleration and provider-specific diagnostics for Core ML, Apple Neural Engine, Metal, command-line tools and model availability.
  • Summary frontmatter now records the transcription provider, model, language and acceleration mode.
  • Choose a specific microphone or follow the current macOS system input automatically.

Improvements

  • Model and provider technology cards in Transcription settings are now collapsible and use much less space.
  • System-audio and microphone meters now share a consistent grid.
  • Russian and English localization has been reviewed and completed for the new settings.
  • If FluidAudio finds no speaker turns, the recognized text is now preserved as one segment instead of failing with an Invalid combined.txt header error.
  • Stalled CLI summarizers that produce no output are stopped after 120 seconds together with their child processes, then the next LLM in the fallback chain is used automatically.
  • The release includes universal binaries for Apple Silicon and Intel Macs.

AnyBrief 2.0.0 for Mac

Signed and notarized release build.

Download DMG