altic-dev /FluidVoice
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight! Android, Linux waitlist open! A local Wispr Flow alternative. Follow https://x.com/fluidvoiceapp for more
★ 13,088⑂ 987👁 47⑃ 477● 701▤ 66
+358
日增长
+358
周增长
+1,068
月增长
13,088
stars
987
forks
47
watchers
477
prs
701
issues
66
releases
README
FluidVoice Free, private dictation that runs on your device. Speak into the apps you already use, clean up your words locally, and keep a searchable record of your meetings. This repository is the macOS app, open source under GPLv3. FluidVoice is also available on other devices through the betas below. Website · Speech models · What’s new · iPhone beta Install with Homebrew: brew install --cask fluidvoice Manual download: latest release [!WARNING] fluidvoice.org is not affiliated with, operated by, or endorsed by FluidVoice or Altic. Its claims to be our official website are unauthorized. Our official website is fluidvoice.com. Our official domains also include altic.dev and fluidvoice.app. For official downloads, use this repository's GitHub Releases. If fluidvoice.org appears in your search results claiming to be our official website, please report the misleading result to the search provider. Get FluidVoice | Platform | Status | Download or join | | --- | --- | --- | | macOS | Available · macOS 15+ | Latest release · brew install --cask fluidvoice | | iOS | TestFlight beta | Join the iPhone beta | | Windows | Beta | Get the Windows beta | | Linux | Early beta | Get the Linux beta | | Android | In progress | Join the waitlist | Features and available models vary by platform. The features below describe the Mac app. [!IMPORTANT] This project is free and open source under GPLv3. If FluidVoice is useful to you, please star the repository — it helps visibility and keeps development going. --- Support FluidVoice If FluidVoice helps you, you can support continued development, model training, and work across platforms on GitHub Sponsors. --- What's New in 1.6.13 - Fluid Speech Pro — our most accurate local dictation model for Apple Silicon. Pro, Mini, and Pico now support 25 languages. - Fluid 1.1 Ripple and Splash — updated on-device text cleanup, with Ripple offering a smaller, faster option for lighter Macs. Both are research previews. - Edit Mode (Beta) — a dedicated local Edit 1.1 model, with its own settings and support for your own AI providers. - Qwen3 ASR 1.7B — another local speech option on Apple Silicon, with automatic detection of 30 languages. - Better FluidMeet — improved call detection, app and microphone selection, Pro-powered transcripts, and the option to redo a saved meeting in another supported language. - Everyday improvements — model recommendations on Dashboard, more reliable text delivery and downloads, improved spoken number formatting, custom accent colors, and shortcuts that distinguish left and right modifier keys. Read the full 1.6.13 release notes. Speech recognition and text cleanup Two separate steps, both available locally: 1. Fluid Speech turns your audio into text. Choose Pro for accuracy, Mini for a smaller download, or Pico for the smallest footprint. 2. Fluid Intelligence optionally cleans up that text: remove fillers and false starts, format lists, and
Top issues
#925[BUG] Fluid Intelligence is unusably slow19 comments · 2026-09-01#852[BUG] Dictation stops detecting microphone input after 3 seconds19 comments · 2026-08-13#479Dictated list not inserted in Claude Code under cmux — only "a" appears (transcript correct; VS Code works)16 comments · 2026-06-29#1273[BUG] Transcription, not pasting in15 comments · 2026-11-02#909Return Key M5 Mac OS26.5.1 in ver 1.6.9 opens Dictate fcn11 comments · 2026-08-27#736[BUG] Cohere Transcribe truncates audio (with fix)11 comments · 2026-07-29#1229[BUG] FluidMeet cannot detect inbound call speaker(s)10 comments · 2026-10-23#948[BUG] FluidVoice accumulates high idle CPU over a long session (204 min CPU time in ~17 h uptime) — M4 Pro10 comments · 2026-09-07
Discussions
#1349Optional idle unloading for larger speech models0 comments · 2026-11-15#1339Allow importing of audio files for transcription/diarisation0 comments · 2026-11-14#1331Add ElevenLabs Scribe as an optional Voice Engine for dictation0 comments · 2026-11-13#1330FluidVoice 1.6.13 crashes on launch on macOS 27.20 comments · 2026-11-13#1319External Teams-to-Browser Transition Causes Silent Loss of Participant Audio Recording0 comments · 2026-11-12#1318Per-app lowercase formatting without an AI provider0 comments · 2026-11-11#1317AssemblyAI Dictation as a cloud transcription option0 comments · 2026-11-11#1315Loving FluidVoice! Best way to keep one Custom Dictionary on two Macs?1 comments · 2026-11-11
Latest release
FluidVoice v1.6.13 v1.6.13 2026-11-13FluidVoice v1.6.13 What's New - Fluid 1.1 Ripple and Splash: updated on-device cleanup, with Ripple offering a faster alternative to Splash. Both are research previews; review your text before sending. - Fluid Speech Pro: our most accurate local dictation model for Apple Silicon. Pro, Mini and Pico support 25 languages. - Edit Mode (Beta): a dedicated Edit 1.1 model on Apple Silicon, with settings separate from dictation and continued support for your own API providers. - Qwen3 ASR 1.7B: on-device dictation on Apple Silicon with automatic detection of 30 languages. - Apple Intelligence for