- Who it helps
- Mac users evaluating local dictation and meeting capture.
- Availability
- The project documents macOS 15 and newer, with model-specific hardware requirements. Microphone and accessibility access are required. Model downloads consume local storage.
Stable and beta differ
Stable 1.6.11, dated October 12, disables meeting summaries over accuracy concerns. The October 13 beta restores summaries with local or user-configured providers. Mini and Pico transcription models are English-only.
Read the component boundaries
The application is GPL-3.0, while Fluid Intelligence is a separate private runtime. Optional cloud providers and documented activity analytics mean privacy depends on configuration and component choice.
What you can do
- Compare the stable and beta release notes, then review model, permission and analytics settings before recording a meeting. Open reference ↗
Where the evidence stops
No audio was recorded or model downloaded. Transcription accuracy, speaker assignment and summary quality were not tested.
Sources read. Sources read October 20, 2026. No installation, model inference or complete external workflow was executed.
Sources & further reading
GitHub · implementation
FluidVoice and FluidMeet ↗
Original evidence for the subject’s scope, availability and limitations.
Altic · page checked 2026-10-20
GitHub · official
FluidVoice stable and beta release notes ↗
Original evidence for the subject’s scope, availability and limitations.
Altic · page checked 2026-10-20
Coverage note: The linked evidence establishes the documented scope. Independent execution and complete YouTube, X and community coverage remain unavailable.
The record over time (1)
Dated source checks and published explanations. An observation date can differ from the original release date.
- · Added to Current
FluidVoice adds FluidMeet meeting transcription, with live captions, speaker labels and searchable text. Summary support depends on the release you choose.