v1.6.9

browser-use/video-usev1.6.9Aug 18, 2026by altic-dev

AI Summary

Focuses on microphone reliability, custom dictionary formatting, and audio parsing fixes for overlapping speakers and AI models.

Key Highlights

Spoken Formatting in Custom Dictionary allows inserting new lines, paragraphs, and symbols using a configurable start word.
Microphone alerts no longer appear on routine startup and can be disabled from settings.
AI responses no longer lose answer text when models emit extra closing thinking tags.
Wired headset microphones remain available in clamshell mode.
Speaker-labeled file transcription no longer drops trailing audio during overlaps.

New Features

Spoken Formatting in Custom Dictionary (configurable start word for formatting)

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