FluidVoice v1.5.11-beta.2

Beta Notice

• This is a beta build and may still have rough edges.
• Please report issues with logs if you hit anything unexpected.

What's New

• Added Parakeet Flash (Beta), a new English-only local streaming dictation model for low-latency live word-by-word transcription. Faster than Parakeet but less accurate but feels INSTANT. Must try!!
• Added OGG file support for file transcription uploads and drag-and-drop.
• Fixed API key authentication for localhost and other local model endpoints that still require an Authorization header.
• Added stronger validation for external Cohere artifacts to catch mismatched input-length contracts earlier instead of failing later during transcription.
• Improved Cohere performance with split Neural Engine/GPU execution and async chunk prefetch, with speedups up to 2x faster on M3 Pro.

Based On

• PR #238: Add OGG file format support for transcription
• PR #233: Update Authorization header logic for API requests

Need Help?

• Report issues: https://github.com/altic-dev/FluidVoice/issues