# FluidVoice

> FluidVoice is a macOS dictation app (macOS 15+, Apple Silicon; Intel via Whisper only) using on-device Parakeet, Nemotron, Cohere, Apple Speech or Whisper models. Since v1.6.11 (October 2026) its FluidMeet feature records meetings locally with live captions, speaker labels and transcripts; meeting summaries are only in the 1.6.12 beta. App code is GPLv3, but the optional Fluid Intelligence model is privately maintained. No Windows or Linux build yet.

- Repository: https://github.com/altic-dev/FluidVoice
- Official docs: https://github.com/altic-dev/FluidVoice#readme
- Checked: 2026-10-15

## What it replaces
- Otter.ai: Meeting transcription, Speaker identification, Meeting summaries (partial). Local meeting transcripts with speaker labels on macOS only; meeting summaries are in the 1.6.12 beta, disabled in stable 1.6.11.
- Granola: Meeting transcription, AI meeting notes (partial). Records and transcribes meetings locally without a bot; summaries only in the 1.6.12 beta; no chat across meetings (a local API lets coding agents read them).

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, native macOS app; transcription runs on-device | https://github.com/altic-dev/FluidVoice#features | 2026-10-15 |
| Code licence | Partial | GPL-3.0 (copyleft) from 2026-02-23; earlier versions Apache-2.0. Fluid Intelligence runtime is private | https://github.com/altic-dev/FluidVoice#license | 2026-10-15 |
| Model weights licence | Partial | Mixed; Whisper MIT, Parakeet CC-BY-4.0; Nemotron, Cohere, Fluid Speech and the private Fluid Intelligence model terms not stated in the README | https://github.com/altic-dev/FluidVoice#fluid-intelligence | 2026-10-15 |
| Commercial use | Partial | GPLv3 app allows commercial use; weights licences vary by model and are not all documented | https://github.com/altic-dev/FluidVoice#license | 2026-10-15 |
| Paid services needed? | Partial | None required; cloud AI enhancement via your own OpenAI, Groq or custom provider key is optional | https://github.com/altic-dev/FluidVoice#quick-start | 2026-10-15 |
| Hardware | Confirmed | Apple Silicon Mac for all models (Intel Macs via Whisper only); ~1 GB disk per voice model, ~3.5 GB for Fluid Intelligence | https://github.com/altic-dev/FluidVoice#requirements | 2026-10-15 |
| Operating systems | Partial | macOS 15+ only; Windows and iOS announced but not released; no Linux | https://github.com/altic-dev/FluidVoice#readme | 2026-10-15 |
| Setup effort | Confirmed | Easy; Homebrew cask or DMG from Releases | https://github.com/altic-dev/FluidVoice#quick-start | 2026-10-15 |

GitHub: 12212 stars, 884 forks, last push 2026-10-16, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/fluidvoice). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.