v1.6.9

huggingface/speech-to-speechv1.6.9Aug 18, 2026by altic-dev

Upgrading?

AI Summary

This release enhances text formatting capabilities in Custom Dictionaries and fixes critical microphone compatibility issues, specifically for wired headsets and Bluetooth devices in clamshell mode.

Key Highlights

  • Spoken Formatting in Custom Dictionary now supports inserting new lines, paragraphs, tabs, and symbols.
  • Wired headset microphones now work correctly in clamshell mode instead of being mistaken for unavailable built-in mics.
  • Fixed External microphones not working when connected through a 3.5mm jack.
  • AI responses no longer lose answer text when a model emits an extra closing thinking tag.

New Features

  • Enhanced Spoken Formatting in Custom Dictionary
  • Improved wired headset compatibility in clamshell mode
  • Fixed external microphone via 3.5mm connection
  • Improved speaker labeling for overlapping audio segments

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