v1.6.9

OpenMOSS/MOSS-Transcribe-Diarizev1.6.9Aug 18, 2026by altic-dev

AI Summary

This release focuses on dictation formatting flexibility, microphone reliability, and AI response handling. Key improvements include support for complex formatting in custom dictionaries and better preservation of speaker labels during audio overlap.

Key Highlights

Spoken Formatting in Custom Dictionary supports new lines, tabs, and symbols via a configurable start word.
Wired headset microphones remain available in clamshell mode.
AI responses no longer lose text when models emit extra closing thinking tags.
Speaker labels are preserved when segments overlap or have brief gaps.

New Features

Spoken Formatting in Custom Dictionary
Disabled Microphone Alerts
Improved AI Response Handling

Full Release Notes

# FluidVoice v1.6.9

## Changes

- Spoken Formatting in Custom Dictionary can insert new lines, paragraphs, tabs, spaces, punctuation, and symbols using a configurable start word
- Microphone alerts no longer appear on routine startup and can be disabled from the alert or Notifications settings.
- AI responses no longer lose answer text when a model emits an extra closing thinking tag.
- Wired headset microphones remain available in clamshell mode instead of being mistaken for the unavailable built-in microphone.
- Fixed External microphones not working when connected through 3.5mm 
- Bluetooth microphones now ride through brief AirPods route and format changes without being marked unavailable
- Speaker-labeled file transcription no longer drops trailing audio when same-speaker segments overlap.
- Speaker labels are preserved when only brief transcription gaps occur, with omitted audio clearly noted.

## Contributors

Thanks to @YuriNachos and @nsutcliffe for fixes and improvements