v1.6.6
thewh1teagle/pyannote-rsv1.6.6Jul 31, 2026by altic-dev
Upgrading?
AI Summary
This update addresses audio reliability and user experience by defaulting to a faster Core Audio path and adding settings to manage silent recordings to improve overall dictation stability.
Key Highlights
- Dictation now uses the faster Core Audio path by default.
- Added an optional setting to skip short, silent recordings.
- Warning added for Bluetooth microphones potentially reducing headphone audio quality.
- Recording overlays now appear faster when dictation starts.
New Features
- Default faster Core Audio path for better reliability.
- Skip short silent recordings setting.
- Edit Mode warning for Fluid-1 incompatibility.
- Improved recording startup latency.
Full Release Notes
# FluidVoice v1.6.6 ## Changes - Recording overlays now appear faster when dictation starts. - Added an optional setting to skip short, silent recordings. ## Fixes - Dictation now uses the faster Core Audio path by default, fixing sped-up audio and improving reliability when microphones switch, disconnect, or reconnect. - Added a warning when Bluetooth microphones may reduce headphone audio quality. - Edit Mode now clearly explains when it cannot be used with Fluid-1. ## Contributors Thanks to @grohith327 for the Core Audio reliability improvements, Bluetooth microphone guidance, and Edit Mode warning in 1.6.6.
Related Repositories
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.
Build smaller, faster, and more secure desktop and mobile applications with a web frontend.
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one