FluidVoice
Free open-source macOS dictation app with fully on-device speech-to-text and a local model that polishes the output
0Visit FluidVoice
altic.dev/fluidAbout FluidVoice
FluidVoice is a free, open-source macOS dictation app that runs speech-to-text entirely on-device, so nothing you say leaves your Mac. You hold a modifier key, speak, and the text lands in whatever field has focus — including terminal applications and coding agents such as Claude Code, which is the use case the product leads with, because dictating a long instruction to an agent is meaningfully faster than typing it. What sets it apart from generic local Whisper wrappers is Fluid-1, a local AI model built specifically to polish dictation output: it applies smart formatting so raw speech becomes clean written text rather than an unpunctuated transcript, and it runs on-device alongside the transcription rather than calling out to a cloud cleanup pass. Install is a Homebrew cask or a direct download, it requires macOS 15.0 or later, and it supports both Apple Silicon and Intel Macs. The site reports over 100,000 downloads. FluidVoice is the first shipped product from ALTIC, a small studio building calm on-device Mac software, whose other listed work includes an MCP server for macOS automation across Safari, Messages, Notes, Reminders, and Calendar, a shipped experimentation tool called Pilot, and two announced-but-unreleased products: FluidWrite, a Mac-native on-device autocomplete for any text field, and Glu, an AI browsing copilot. iOS and Windows versions are listed as available paths from the download page.
Does ChatGPT recommend your AI tool?
If you're building in Audio & Music, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.
Studio-grade AI voices and speech-to-text — the voice layer most teams pair with tools like this.
Key Features
FluidVoice Pros & Cons
✅ Pros
- +Genuinely private — no cloud round trip at any stage
- +The polish model is the differentiator over plain local Whisper
- +Free with no account or usage caps
- +Dictating prompts to coding agents is a real speed win
⚠️ Cons
- −macOS 15.0+ only for the main app
- −On-device models are typically less accurate than the largest cloud ones
- −Made by a very small studio, with several sibling products still unreleased
Who Is FluidVoice Best For?
Tags
Is FluidVoice your tool?
This is the page buyers and AI assistants read when they look up FluidVoice. Claim your listing for $19 one-time — no subscription, nothing to cancel — and get a Featured badge, top placement in your category, and a permanent dofollow backlink. Prefer it ongoing? Monthly is one click away on the next page.
Complete Your Audio Production Stack
Other audio production tools in our catalog:
ElevenLabs
Try FreeUltra-realistic AI voiceovers
Add professional narration to your videos
Murf.ai
Try FreeStudio-quality AI voices
Create voiceovers in 120+ voices
AdCreative.ai
Try FreeAI-powered ad creatives
Generate marketing visuals in seconds
💰 Affiliate disclosure: We may earn a commission if you sign up through these links at no extra cost to you.
Stay updated on Audio & Music tools — join our weekly newsletter
One concise email with fresh launches, trending picks, and featured standouts.
Alternatives to FluidVoice
View all FluidVoice alternatives →More Audio & Music tools
GetTranscribe
Transcribes and structurally analyses social video — hooks, scenes, patterns
MusicGPT
AI music generation with remix, stems, sound FX, TTS and commercial use
Typecast
Expressive AI text-to-speech with emotion control, voice cloning and an API
Free ai Music Creator
Create songs and background music from text prompts.
Harku YouTube to Text
Turn YouTube videos into timestamped transcripts and downloadable subtitle files.
RailCall
Local-first agent runtime with human approval and signed execution records.
Agent connectivity: not yet verified