v1.6.9

fregante/GhostTextv1.6.9Aug 18, 2026by altic-dev

Upgrading?

AI Summary

This release enhances formatting capabilities in Custom Dictionary and improves microphone handling in clamshell and Bluetooth scenarios. Fixes address AI response truncation and transcription gaps to ensure data integrity.

Key Highlights

  • Spoken Formatting supports new lines, paragraphs, and symbols via start word
  • AI responses no longer lose text when emitting extra closing thinking tags
  • Wired headset microphones now work in clamshell mode
  • Bluetooth microphones ride through AirPods route changes
  • Speaker-labeled transcription fixes for overlapping segments and gaps

New Features

  • Configurable start words for Spoken Formatting in Custom Dictionary
  • Microphone alerts can be disabled from Notifications settings
  • Fixed External microphones working through 3.5mm jack

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

Related Repositories