FluidVoice v1.6.12

FluidVoice is a free and open source voice-to-text application for macOS that brings fast, local AI-powered dictation to virtually any app. Designed with privacy and performance in mind, it performs speech recognition directly on your Mac, allowing users to dictate text into documents, emails, chat applications, code editors, and more without relying on cloud-based transcription services.

Unlike many dictation tools that require subscriptions or send recordings to remote servers, FluidVoice adopts a local-first approach. It supports multiple on-device speech recognition models, including Parakeet, Whisper, Apple Speech, and Cohere Transcribe, allowing users to choose between speed, language support, and transcription accuracy. Optional AI enhancements can be enabled using providers such as OpenAI or Groq, but these features are entirely optional.

The application integrates seamlessly with macOS, enabling users to dictate directly into nearly any text field using a global keyboard shortcut.

Key Features of FluidVoice

Local AI Speech Recognition

FluidVoice performs transcription locally whenever supported models are used. This improves privacy while reducing latency, making dictation feel nearly instantaneous on Apple Silicon Macs.

Multiple Speech Models

Users can choose from several transcription engines, including Apple Speech, Whisper, NVIDIA Parakeet, and Cohere models. This flexibility allows users to balance speed, hardware requirements, and multilingual support according to their needs.

Universal Dictation

The application works across virtually any macOS application. Whether writing emails, editing documents, chatting in Slack, coding in an IDE, or taking notes, FluidVoice can insert text directly into the active application.

Command Mode

One of the standout additions is Command Mode, which enables voice commands to perform actions on macOS beyond simple dictation. This expands the application into a lightweight voice assistant for productivity workflows.

AI Text Enhancement

Raw dictation can be automatically cleaned up with optional AI processing. Grammar correction, punctuation, rewriting, and formatting are available when compatible AI providers are configured.

Open Source

FluidVoice is fully open source, allowing developers and security researchers to inspect the codebase, contribute improvements, and verify its privacy claims.

Download FluidVoice v1.6.12 - Software Mirrors

FluidVoice v1.6.12 for macOS

Fluid-oss-1.6.12.dmg | 72.75 MB

Fluid-oss-1.6.12.zip | 72.95 MB

FluidVoice v1.6.12 Release Notes:

FluidVoice v1.6.12

FluidMeet

  • New Meeting, settings and history stay visible inside the meeting page. Starting another meeting waits for a running summary to finish or be cancelled. #1156
  • Set your own start/stop meeting shortcut in Shortcuts settings; unassigned by default. Uses the saved meeting source. #1157
  • Export transcripts as Markdown (.md), Text or JSON, with timestamps and speaker names. #1158
  • Preserve microphone recordings from devices that provide integer audio formats. #1152
  • Clearer microphone speech when other audio is playing. If echo filtering is unavailable, keep the speech and show a small possible-echo notice.
  • Live captions finish phrases before recovering from a stall, with fewer interruptions. Floating captions can be dragged on macOS 27. Thanks to @argus-vault for the dragging fix. #1061
  • Preserve recognized words near sentence endings and join unlabelled fragments to the preceding speaker.
  • Edit text in place with a double-click. Rename and merge speakers from Edit speakers, confirm merges, and use Command-Z to undo corrections. #1187
  • Meeting history loads details as needed instead of reading every recording up front.
  • Keep processing versions consistent across saved meeting runs.
  • Turn FluidMeet on or off from its settings without deleting saved meetings.
  • Summaries can run on this Mac or with your own AI provider, with an optional custom prompt, and stay available after restarting the app.
  • AI summaries show a brief accuracy reminder.
  • Let Claude Code, Codex and other coding agents read meetings from FluidMeet settings → Integrations.
  • Browser meetings are detected by default. End reminders cover manual recordings and Safari Meet even with automatic start detection off; confirmed call exits prompt sooner.

Other changes and fixes

  • Updated the app icon with a silver mark and subtle edge shine. #1221
  • Reduced startup delays when starting dictation.
  • Dictionary + opens Add Manually without blocking normal dictation. Compact buttons keep the list tidy; Test word stays inside the Edit popup.
  • Dictionary learning has clearer recording and save steps, pauses between examples, and editable spelling corrections.
  • Clearer correction labels, accurate dictionary search counts, and feedback when nothing new is saved. #1151, #1165
  • User dictionary spellings override defaults. Pending learned rules are cancelled when text is edited or observation ends.
  • Saved dictionary pronunciations carry across Parakeet, Mini and Pico. Pronunciation learning is now on by default. Dictation keeps its normal processing until a voice word is trained.
  • Selecting Fluid Speech Mini or Pico no longer shifts the Voice Engine page upward.
  • Refresh idle AI connections to avoid stalls on the next request. Thanks to @andrewmitchell-automations. #1134
  • Switch between Dictation, Edit and Command during a recording without a false “Dictation Unavailable” alert or restarting capture. Preserve the starting field during mode changes.
  • Paste shortcut tests now reject unexpected modifier keys. #1193
  • Disabled Command and Paste Last shortcuts no longer block reusing their keys. #1213
  • Recovery Copy uses the current transcript and restores the retry window when copying fails. #1198
  • Recovery and microphone-change popups stop redrawing after their countdown ends, reducing idle CPU use. #1218
  • Login launches keep the main window hidden when requested, including after a restart. Opening FluidVoice from the menu bar reuses that window.
  • Fluid Intelligence model downloads retry brief network interruptions and resume saved progress. Working models stay available during a failed update.
  • Fixed AI requests to newer Claude models that reject a temperature setting.

Contributors

Thanks to @andrewmitchell-automations, @grohith327, @argus-vault, @yyjosef, @dxcore35 and @nickbecker for 1.6.12 fixes, improvements and reports.

Performance and User Experience

FluidVoice delivers an impressive user experience, especially on Apple Silicon hardware. Dictation starts quickly, transcription appears with minimal delay, and the lightweight interface stays out of the way during everyday work.

The application integrates well with macOS through menu bar controls, global shortcuts, and accessibility features. Users who spend long hours writing documentation, emails, or code can significantly reduce keyboard usage.

Community feedback has also been overwhelmingly positive, with many users praising its performance, privacy, and the fact that it remains completely free and open source.

Pros

  • Completely free and open source.

  • Local-first speech recognition for improved privacy.

  • Extremely fast transcription on Apple Silicon.

  • Supports multiple AI speech models.

  • Works across nearly all macOS applications.

  • Optional AI-powered text enhancement.

  • Active development with frequent updates.

Cons

  • Primarily optimized for macOS.

  • Best performance requires Apple Silicon hardware.

  • Some advanced AI features require external API keys.

  • Initial model downloads can consume significant disk space.

Who Should Use FluidVoice?

FluidVoice is ideal for writers, developers, students, journalists, content creators, and professionals who spend significant time typing on a Mac. It is especially valuable for users seeking a private, subscription-free alternative to commercial dictation software.

Those who prioritize offline processing and open source software will find it particularly appealing.

Final Verdict

FluidVoice demonstrates that high-quality voice dictation does not require expensive subscriptions or cloud processing. Its combination of local AI transcription, excellent performance, broad application compatibility, and active open source development makes it one of the strongest dictation solutions available for macOS.

For Mac users looking for a fast, privacy-focused voice-to-text application, FluidVoice is an outstanding choice.

FluidVoice v1.6.12
Free
Download

Software Informations:
Developer:

Operating System:
macOS
Date Added:
2026-10-23T03:07:18.545Z
Categories:

Post a Comment/Report Broken Link: