FluidVoice
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows pre-build available! A local Wispr Flow alternative. DM
What is FluidVoice?
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows pre-build available! A local Wispr Flow alternative. DM us on X exclusive model access! 😉 - https://x.com/fluidvoiceapp
Overview of FluidVoice
What it is
FluidVoice is an open source voice-to-text dictation app for macOS with on-device AI enhancement. It supports multiple speech models and offers a local-first approach. The app also includes a separate private local AI runtime called Fluid Intelligence for advanced dictation enhancement.
Key features
- Fluid Intelligence: on-device AI enhancement for smart formatting, context-aware capitalization, and post-processing, all running locally on your Mac with zero data leaving your machine.
- Command Mode: control your Mac by voice: launch apps, run shortcuts, trigger system actions, and automate workflows without touching the keyboard.
- Write Mode: write or rewrite text directly in any text field across any app. Select text and rewrite it, or dictate new content inline.
- Multiple Speech Models: Nemotron Speech 3.5, Parakeet Flash, Parakeet TDT v3 & v2, Cohere Transcribe, Apple Speech, and Whisper. Pick the model that fits your language and latency needs.
- Live Preview: real-time transcription overlay with notch support, so you see words appear as you speak.
- Local-First: your voice and text never leave your machine unless you opt in to a cloud AI provider.
- Global Hotkey: instant voice capture from anywhere, no app switching needed.
Use cases
FluidVoice can be used for dictation in any application, controlling the Mac via voice commands, rewriting text, and automating workflows. It is suitable for users who want on-device dictation without sending data to the cloud. The app supports multiple languages and models for different accuracy and latency requirements.
Getting started
Install with Homebrew: bash brew install --cask fluidvoice Or download the latest release from the repository. Grant microphone and accessibility permissions when prompted. Set a global hotkey in settings and go through the onboarding to choose a voice model.
License and pricing
FluidVoice is free and open source under the GPL-3.0 license. The core dictation experience is free. Fluid Intelligence is a separate private local AI runtime, but the app works without it. There is no stated pricing for Fluid Intelligence; it is currently private.
Based on the project's public README and repository metadata.
