back to top
HomeSoftwareFluidVoice: AI Voice-to-Text Dictation App for macOS

FluidVoice: AI Voice-to-Text Dictation App for macOS

- Advertisement -

File Info

FileDetails
NameFluidVoice
Versionv1.6.0
DeveloperALTIC
LicenseGNU GPL v3
File SizeVaries by release
File FormatDMG
PlatformmacOS
CategoryProductivity, Voice & Speech Recognition
Github Repositoryaltic-dev/FluidVoice

Description

If you spend hours writing emails, documents, code, or notes, typing everything can quickly become exhausting. FluidVoice makes dictation feel much more natural by turning your voice into text with fast, accurate speech recognition and optional on-device AI enhancements.

Its built with a local-first approach. Most speech models run directly on your Mac, and its optional Fluid Intelligence engine improves formatting, punctuation, and capitalization without sending your voice recordings to external servers.

If you’re writing articles, coding, replying to messages, or simply prefer speaking over typing, FluidVoice offers a fast and privacy-friendly dictation experience for macOS.

Use Cases

  • Dictate emails, documents, and notes much faster than typing.
  • Write code comments, documentation, or blog posts using your voice.
  • Control Mac actions with voice commands and shortcuts.
  • Improve transcripts locally without relying on cloud AI services.
  • Create a privacy-focused speech-to-text workflow that works offline.

Screenshots

Features of FluidVoice

FeatureDescription
Voice-to-Text DictationConvert speech into text with fast and accurate AI speech recognition.
Fluid IntelligenceOptional on-device AI for smarter formatting, capitalization, and punctuation.
Command ModeControl your Mac with voice commands to launch apps, run shortcuts, and automate tasks.
Write ModeDictate or rewrite text directly inside virtually any application.
Live PreviewView real-time transcription in a floating overlay while speaking.
Multiple Speech ModelsChoose from Apple Speech, Whisper, Nemotron, Parakeet, and Cohere models.
Global HotkeyStart dictation instantly from anywhere using a customizable shortcut.
Audio HistoryOptionally save local recordings and export them as ZIP archives.
AI EnhancementEnhance transcripts using local AI or optional cloud providers like OpenAI and Groq.
Menu Bar IntegrationAccess controls and settings directly from the macOS menu bar.
Local-First PrivacyVoice recordings stay on your Mac unless you choose a cloud provider.
Automatic UpdatesReceive seamless app updates with an optional beta channel.
Related: Handy: Offline Open-Source Speech-to-Text AI App For Windows, macOS & Linux

System Requirements

ComponentRequirement
Operating SystemmacOS 15.0 Sequoia or later
ProcessorApple Silicon recommended (Intel supported with Whisper models)
RAM8 GB minimum (16 GB recommended for larger AI models)
StorageAround 1 GB for speech models, up to 3.5 GB for optional Fluid Intelligence
PermissionsMicrophone and Accessibility permissions required

Installation

  1. Download the DMG file.
  2. Open the DMG and drag FluidVoice into the Applications folder.
  3. Launch the app and grant Microphone and Accessibility permissions.
  4. Choose your preferred speech recognition model during setup.

Supported Speech Models

ModelBest ForLanguage Support
Apple SpeechNative macOS dictationSystem languages
WhisperBroad compatibilityUp to 99 languages
Nemotron Speech 3.5Fast multilingual dictation~40 languages
Parakeet FlashUltra-low latencyEnglish
Parakeet TDT v3Fast multilingual dictation25 languages
Parakeet TDT v2Fast English dictationEnglish
Cohere TranscribeHigh accuracy14 languages

Download FluidVoice

Why FluidVoice?

FluidVoice is one of the few open-source dictation apps that combines fast speech recognition with optional local AI enhancements while keeping your voice data on your own device. If you want a privacy-focused alternative to cloud-based dictation tools, it’s an excellent choice for writing, coding, note-taking, and everyday productivity.

Don’t miss any Tech Story

Subscribe To Firethering NewsLetter

You Can Unsubscribe Anytime! Read more in our privacy policy

LEAVE A REPLY

Please enter your comment!
Please enter your name here

YOU MAY ALSO LIKE
World Monitor Open-Source Global Intelligence Dashboard with AI News & Live Maps

World Monitor: Global Intelligence Dashboard with AI News & Live Maps

0
If you regularly follow world news, financial markets, technology, or geopolitical developments, World Monitor offers a much more organized way to stay informed. Its combination of AI-powered summaries, interactive maps, market data, and optional local AI support makes it a powerful desktop dashboard for researchers, analysts, journalists, and everyday users who want a broader view of what's happening around the world.
Palmier Pro AI video editor and generator app

Palmier Pro: AI-Powered Video Editor for macOS

0
AI video generators have become incredibly capable, but the workflow is still fragmented. You generate a clip in one tool, download it, import it into an editor, make changes, then repeat the entire process whenever you need a revision. Palmier Pro aims to eliminate that loop. Instead of treating AI as a separate website, it brings generation directly into the editing timeline. You can create AI videos, images, and audio alongside your own footage without constantly switching between different applicationsm, this way AI becomes another creative tool. Beyond generation, Palmier Pro is also a fully featured video editor built natively with Swift for Apple Silicon Macs. It supports multi-track editing, timeline controls, professional exports, and even lets AI agents like Claude, Cursor, and Codex interact with your projects through MCP.
Amuse Easily Run AI Image, Video, Audio & Text Models Locally on Windows

Amuse: Easily Run AI Image, Video, Audio & Text Models Locally on Windows

0
Running AI models locally usually means dealing with Python environments, dependency conflicts, model downloads, and complex tools like ComfyUI. Amuse got you covered if you don't want any hurdle of spending hours configuring workflows, you install the app, pick a model, and start generating. The software automatically handles its own isolated Python environment while providing a clean desktop interface for image generation, video creation, speech recognition, voice synthesis, upscaling, interpolation, and AI-powered editing. It acts more like a local AI studio, bringing together popular image, video, audio, and text models under one interface.