New · Fluid-1 model now available

FluidVoice gives you the app.

FluidVoice is a free, open-source Mac dictation app with Fluid-1, the best local AI model for polishing dictation.

$brew install --cask fluidvoice
Watch demo
—
On-device AIZero data leaves your MacSmart formatting

50,000+ downloads · macOS 15.0+ · Apple Silicon & Intel

Watch FluidVoice and Fluid Intelligence work

Speed demo preview

Raw FluidVoice dictation — speech hits the terminal as fast as you can talk.

Try it yourself

Take FluidVoice for a spin

Press ⌥ to dictate into Claude Code.

macOS Sonoma Wallpaper
Claude Code
Fri 9:41 AM
Claude Code v2.1.12
▐▛███▜▌ ▝▜█████▛▘ ▘▘ ▝▝
Welcome back!
Opus 4.5 · Claude Team · FluidVoice
~/dev/contact-form
❯ ▍
Read(ContactForm.tsx)
Read 156 lines
I'll fix both issues — email validation and
a loading spinner on submit.
Update(ContactForm.tsx)
──────────────────────────────────────────────────────────────────────
Edit file ContactForm.tsx
╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
22 const handleSubmit = async (e) => {
23 e.preventDefault();
24 + if (!validateEmail(email)) {
+ setError('Please enter a valid email');
+ return;
+ }
25 }
Bash(npm test)
4 passed

Tap the button, or press the Option key on your keyboard

App + model

Two layers, one local workflow

Most open-source dictation apps stop at transcription. Most polished dictation apps send text to the cloud. FluidVoice pairs an open-source Mac app with Fluid-1, a local model for post-processing.

FluidVoice

The open-source macOS app: hotkey, overlay, local speech models, typing into any app, command mode, write mode, history, settings, and community-visible code.

Fluid-1

The local intelligence layer: cleans up rough dictation, adapts tone per app, formats structure, fixes casing, handles dates/names/numbers, and keeps data on-device.

Loved by the community

From developers to multilingual teams

50,000+

Downloads

Fluid-1

On-device AI model

Free

Forever, no tiers

GPLv3

Open source

40+

Languages

What's inside

Powerful features, seamlessly integrated

Works offline

Local speech models process everything on-device. No Wi-Fi, no problem.

Fluid Intelligence

On-device AI polishes formatting, capitalization, and post-processing. Zero data leaves your Mac.

Predefined modes

Write Mode, Command Mode, and Direct Dictation - switch context instantly.

Multilanguage support

40+ languages across models. From Nemotron to Whisper, speak naturally in your language.

System-wide input

One shortcut, any text field. Email, docs, chat, terminal, and code editors all work the same.

Real-time speed

Speaking is ~3.7x faster than typing. Text lands instantly so ideas stay in motion.

Apple Silicon optimized

CoreML and Metal deliver low-latency transcription while preserving battery efficiency.

AI post-processing

Local or cloud — Fluid Intelligence, OpenAI, Groq, or custom providers. You choose.

Adaptive tone

Different apps, different tone

Customize prompts for each app so your dictation fits the context.

You said

“hey so um the deploy broke because of the config change from yesterday, I fixed it but we should probably review those before pushing to prod going forward”

#engineering
R

Rohit 9:42 AM

hey team — deploy broke from yesterday's config change. fixed it now, but we should probably start reviewing configs before pushing to prod 🙏

Tone: Casual
New Message

To: team@company.com

Subject: Deployment Issue Resolved

Hi team, the deployment failed due to a configuration change made yesterday. I have resolved the issue. Going forward, I recommend we review configuration changes before deploying to production.

Tone: Formal
Issue #142

Deployment failed — config change

## Issue

Deployment failed due to config change (ref: yesterday's PR).

## Resolution

- Fixed and verified in staging

- Prod deploy restored

## Action item

Require config review before prod push.

Tone: Structured
Quick Notes

deploy broke from yesterday's config change. fixed it. need to set up config review before prod pushes going forward.

Tone: Personal

Customize per app

Write custom prompts for any app. Slack casual, Mail formal, GitHub structured — you define it.

Detects the app

FluidVoice recognizes which app is focused and selects the matching tone profile automatically.

Same voice, right tone

Speak naturally. Fluid-1 rewrites your words to fit the context without changing your meaning.

Integrations

Works anywhere you can type

Cursor, Slack, Notion, Chrome, Discord, Ghostty… You say it, FluidVoice handles it.

Cursor
Slack
Notion
Chrome
Discord
Ghostty
Terminal
Mail
Messages
VS Code
Xcode
Notes

Performance

Built for speed you can feel

FluidVoice keeps inference local and latency low so your writing flow stays uninterrupted.

Up to 3,380x

Real-time factor

Peak throughput varies by hardware, model, and audio length.

<100ms

Perceived latency

Fast enough to feel immediate while moving through thought-heavy tasks.

Local

Local-first dictation

Local speech models keep dictation on-device; optional AI providers are user-controlled.

Multi-hour

Long-form windows

Handles extended transcription sessions without manual chunking.

Architecture highlights

Model lineup spans Nemotron Speech 3.5, Parakeet Flash, Parakeet TDT v3/v2, Cohere Transcribe, Apple Speech, and Whisper, with optimized routing to keep transcription responsive across short bursts and long dictation sessions.

Nemotron Speech 3.5 — Ultra Fast Low LatencyNemotron 3.5 MultilingualParakeet Flash (Beta)Parakeet TDT v3Parakeet TDT v2Cohere TranscribeApple SpeechWhisper Tiny / Base / Small / Medium / Large

What the community says

Loved by developers, built for how you work

Free forever

“Thank you for making it free, forever! Hope to see it support more languages soon!”

GitHub discussion

Community-first growth

“Very nice! I imagine monetization in future might be easier cause you're being distributed for free. Smart plan.”

Early adopter

Open source trust

“Thanks for making it open source”

Developer comment

Multilingual reliability

“It works fine in German by the way (Tahoe, Mac Mini M2 Pro, external mic). This opens a host of new possibilities for interacting with my Mac.”

German workflow

Intent recovery

“Wow, impressive. I stumbled while dictating and the transcriber caught it and output the word I had intended to say!”

Daily dictation

Head-to-head speed

“This is a really impressive app, speedy and accurate. It's just as good as Wispr Flow in my testing.”

Comparison test

Product polish

“This is unbelievably slick. Congrats, and well done.”

Launch feedback

Open source goodwill

“Solid product! and super cool of you to make it open source :)”

Community comment

Language + media

“I just did a quick test in French using dictation and also tried transcribing a video — both worked very well.”

French test

Developer adoption

“Love the project. Thanks for building this!”

GitHub reaction

Retention

“Having been one of the early users, I want to say thank you and amazing job!”

Early user

Momentum

“All the best of success with this. Congrats :)”

Community support

Free forever

“Thank you for making it free, forever! Hope to see it support more languages soon!”

GitHub discussion

Community-first growth

“Very nice! I imagine monetization in future might be easier cause you're being distributed for free. Smart plan.”

Early adopter

Open source trust

“Thanks for making it open source”

Developer comment

Multilingual reliability

“It works fine in German by the way (Tahoe, Mac Mini M2 Pro, external mic). This opens a host of new possibilities for interacting with my Mac.”

German workflow

Intent recovery

“Wow, impressive. I stumbled while dictating and the transcriber caught it and output the word I had intended to say!”

Daily dictation

Head-to-head speed

“This is a really impressive app, speedy and accurate. It's just as good as Wispr Flow in my testing.”

Comparison test

Product polish

“This is unbelievably slick. Congrats, and well done.”

Launch feedback

Open source goodwill

“Solid product! and super cool of you to make it open source :)”

Community comment

Language + media

“I just did a quick test in French using dictation and also tried transcribing a video — both worked very well.”

French test

Developer adoption

“Love the project. Thanks for building this!”

GitHub reaction

Retention

“Having been one of the early users, I want to say thank you and amazing job!”

Early user

Momentum

“All the best of success with this. Congrats :)”

Community support

FAQ

Frequently asked questions

Yes. FluidVoice is completely free and open source.
FluidVoice requires macOS 15.0 Sequoia or later, plus microphone access and accessibility permissions for typing.
Yes. Current version supports Intel Macs by using Whisper models.
FluidVoice supports Nemotron Speech 3.5 (Ultra Fast Low Latency and Multilingual), Parakeet Flash (Beta), Parakeet TDT v3, Parakeet TDT v2, Cohere Transcribe, Apple Speech, and Whisper Tiny/Base/Small/Medium/Large.
Fluid Intelligence is a local AI runtime which runs the Fluid-1 model. It delivers advanced on-device dictation enhancement — smart formatting, context-aware capitalization, adaptive tone based on the active app, and post-processing — all running locally on your Mac. It is fully optional (~3.5 GB download), requires no cloud or API keys, and no data leaves your machine. FluidVoice works great on its own without it.
Language support is model-specific: Nemotron Speech 3.5 supports ~40 languages, Parakeet Flash and Parakeet TDT v2 are English-only, Parakeet TDT v3 supports 25 languages, Cohere Transcribe supports 14 languages, Apple Speech depends on macOS system languages, and Whisper supports up to 99 languages depending on model size.
FluidVoice is local-first and uses local speech models for dictation. AI enhancement can use optional providers such as OpenAI, Groq, or custom providers, so cloud use depends on the features and providers a user enables.
FluidVoice needs microphone access for voice capture and accessibility permissions for typing into other apps.
From 2026-02-23 onward, FluidVoice is licensed under the GNU General Public License v3.0 (GPLv3). Versions before that date used Apache License 2.0.
Optional anonymous analytics, FluidVoice does not collect voice, raw audio, transcribed text, prompts etc. No sensitive info leaves your mac
You can click the download button or get the latest release at https://github.com/altic-dev/Fluid-oss/releases/latest.