FluidVoice v1.5.12

FluidVoice v1.5.12

What's New

• Reworked dictation into two configurable shortcuts, each with its own custom prompt( AI ON ) and just raw transcription ( AI OFF) as needed.
• Unified AI on/off and custom prompts to avoid cofusion. Now AI prompt equates to AI enhancement off. So you can toggle AI on/off on the fly with a shortcut as needed or add a separate shortcut for OFF and ON!
• Fixed overlay actions staying functional after the main settings window closes.
• Added a compact Backup & Restore utility in Preferences for quicker export and import access between devices or for backup!
• Added a configurable Cancel Recording shortcut in Settings, defaulting to Escape, so recording cancel behavior can be remapped.
• Added microphone switching to the menu bar for quicker input-device changes without opening Settings.

Voice Engine Updates

• First Voice app to add Cohere Transcribe as a new speech model option. Very accurate with punctuations and numbers. But a little slower. Give it a try and let me know how you like it! ( 14 languages but needs manual selection)
• Added Parakeet Flash (Beta), an even faster English-only local streaming model for low-latency live dictation.
• Improved Cohere performance with split Neural Engine/GPU execution and async chunk prefetch.
• Fixed Cohere model downloads and transcription failures.
• Added manual language selection for Cohere in Voice Engine settings.
• Added stronger validation for external Cohere artifacts so mismatched model contracts fail earlier and more clearly.
• Added deeper Parakeet Flash diagnostics for cache resolution, missing model files, and download/load verification to make stuck Loading model... failures easier to trace.

File and Meeting Transcription

• Added OGG support for file transcription uploads and drag-and-drop.
• Expanded meeting transcription format support with broader macOS-native audio and video compatibility.

Other Fixes

• Added manual backup export and import for app settings, prompt profiles, transcription history, and stats, with API keys excluded from backup files.
• Synced microphone selection state between the menu bar and Settings.
• Made Launch at startup more robust.
• Fixed API key authentication for localhost and other local model endpoints that still require an Authorization header.
• Fixed the top notch overlay so it shows the active prompt name correctly during prompt-mode recording.
• Fixed shortcut reassignment so pressing an already-assigned shortcut rebinds it cleanly instead of triggering the live recording action.
• Fixed modifier-only shortcuts so multi-modifier combos like fn + control can be recorded and matched correctly.

Credits

• Thanks to @yelloduxx for the original prompt-mode and overlay work.
• Thanks to @kabhijeet for the localhost API auth fix in PR #233.
• Thanks to @daaain for the media format support contribution.
• Thanks to all others I've missed for suggestions and contributions!

Need Help?

• Report issues: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.11-beta.3

FluidVoice v1.5.11-beta.3

Beta Notice

• This is a beta build and may still have rough edges.
• Please report issues with logs if you hit anything unexpected.

What's New

• Fixed Cohere model downloads and transcription failures.
• Added manual Language change option in Voice Engine for Cohere.
• Added dynamic Meeting Transcription format support, including OGG and broader macOS-native audio/video compatibility. Thanks to @daaain for the contribution.

Need Help?

• Report issues: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.11-beta.2

FluidVoice v1.5.11-beta.2

Beta Notice

• This is a beta build and may still have rough edges.
• Please report issues with logs if you hit anything unexpected.

What's New

• Added Parakeet Flash (Beta), a new English-only local streaming dictation model for low-latency live word-by-word transcription. Faster than Parakeet but less accurate but feels INSTANT. Must try!!
• Added OGG file support for file transcription uploads and drag-and-drop.
• Fixed API key authentication for localhost and other local model endpoints that still require an Authorization header.
• Added stronger validation for external Cohere artifacts to catch mismatched input-length contracts earlier instead of failing later during transcription.
• Improved Cohere performance with split Neural Engine/GPU execution and async chunk prefetch, with speedups up to 2x faster on M3 Pro.

Based On

• PR #238: Add OGG file format support for transcription
• PR #233: Update Authorization header logic for API requests

Need Help?

• Report issues: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.11-beta.1

FluidVoice v1.5.11-beta.1

Beta Notice

• This is a beta build and may still have rough edges and the new model might have issues.
• Please report issues with logs if you hit anything unexpected.

Changes

• First Transcription app to add Added Cohere Transcribe to the models list.
• Cohere Transcribe added a new recommended model with existing Parakeet options.

Notes on Cohere

• https://huggingface.co/CohereLabs/cohere-transcribe-03-2026
• Current version can transcribe 40 minute audio/video in ~1 minute.
• Supports 14 languages : European: English, French, German, Italian, Spanish, Portuguese, Greek, Dutch, Polish
  AIPAC: Chinese (Mandarin), Japanese, Korean, Vietnamese
  MENA: Arabic
• Original size 4GB - Converted to 1.7GB (6 bit) for FluidVoice users
• Little slower than Parakeet but very accurate. please do give it a try and let me know how it goes!
• If Intel users want to try this - message on discord and we can experiment to see how it works.

Help Us Improve

• Report issues here: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.10

FluidVoice v1.5.10

What's New

• Improved Reliable Paste so clipboard restore waits for stronger verification.
• Reduced wrong-clipboard pastes in slower or less Accessibility-friendly apps by extending the restore fallback window.
• Added an opt-in beta updates setting.
• Fixed Cmd+V paste for non-QWERTY keyboard layouts like Dvorak, Colemak, and AZERTY.
• Added transcription sound volume controls in Settings.
• Added app-aware custom prompt configuration for AI and dictation behavior.
• Fixed several Swift concurrency issues and general build stability problems.
• Fixed light-mode readability issues in overlay menus and popups.

Thanks

• Thanks to @grohith327, @poiesb, @yelloduxx, and @nnkaz1k for the contributions that helped shape this release.

Need Help?

• Report issues: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.9

FluidVoice v1.5.9

This release focuses on speed, stability, polish updates and bug fixes.

What's New

• FluidVoice Parakeet is even faster now - now reduced from ~300ms -> <~100 ms dictation speed! 🚀🚀🚀
• Added a new text insertion mode setting with Reliable Paste for more dependable dictation insertion across browsers and desktop apps.
• Added new FluidVoice onboarding flow for new users.
• Improved Getting Started so the final setup step scrolls directly to the test playground.
• Clarified Parakeet TDT v3 language support with visible short codes in onboarding and voice engine settings. #124
• Added an Accessibility fallback message and restart button when macOS does not restart the app automatically.
• Added persistent history for file transcriptions. (Contributor: @hazzahex)
• Merge transcription sound toggle into picker with a None option. (Contributor: @moogman)
• Improve file transcription upload UX by making the full upload area tappable, adding drag-and-drop support, and validating dropped file types. (Contributor: @hazzahex)
• Hardened media playback pause/resume against duplicate callback crashes. (Contributor: @guard22)
• Other minor bug fixes

Need Help?

• Report issues: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.8

FluidVoice v1.5.8

This release consolidates the improvements from the 1.5.7 beta builds into one stable update.

https://github.com/altic-dev/FluidVoice/releases/tag/v1.5.7-beta.1
https://github.com/altic-dev/FluidVoice/releases/tag/v1.5.7-beta.2
https://github.com/altic-dev/FluidVoice/releases/tag/v1.5.7-beta.3

What's New

• Better overlay experience with cleaner layout and less clutter.
• Improved stability during dictation, especially when using custom vocabulary.
• Easier recovery tools: quicker issue reporting and improved rollback options.
• Vocabulary Boosting is now optional (off by default), while Instant Replacement still works as usual.
• New preference: hide FluidVoice from the Dock and Cmd+Tab when you want a menu-bar-only setup.

Small Quality Improvements

• Settings section renamed to Overlay for clarity.
• Current app version is now shown in Automatic Updates.

Need Help?

• Report issues: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.7-beta.3

FluidVoice v1.5.7-beta.3

Beta Notice

• This is a beta build and may be unstable.
• Please report any issues with logs.

Changes

• Improved compact overlay layout for medium size: cleaner labels, shorter AI chip, reduced clutter.

Help Us Improve

• Report issues here: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.7-beta.1

FluidVoice v1.5.7-beta.1

Beta Notice

• This is a beta build and may be unstable.
• Please test at your own risk.
• If you test this build, we would really appreciate bug reports with logs.

What's New in This Beta

• Forced log collection is enabled by default to improve crash/debug visibility.
• Added a quick Report Issue entry point (bug icon) to open GitHub Issues faster.
• Rollback flow improved:
  • Roll back to locally available previous build when present.
  • If local rollback is not found, you can open previous build links from recent releases.
• Added manual fallback access to recent previous builds (last stable releases) for easier recovery.
• Rollback confirmation flow now includes a direct path to report bugs.

Stability Notes

• This beta focuses on recoverability and diagnostics after the 1.5.7 issues.
• Crash and failure investigation should now be easier with default log persistence.

Help Us Improve

• Report issues here: https://github.com/altic-dev/FluidVoice/issues
• Include what you were doing, expected behavior, and anything unusual before failure.

FluidVoice v1.5.7

Note: This release includes all planned v1.5.6 improvements.

Major Features

Expanded Overlay Experience

• Introduced a significantly improved large overlay with richer, in-context controls.
• Upgraded small and medium overlays with cleaner UX, better alignment, and more consistent behavior.
• Overlay now acts as a true control surface for dictation and editing workflows.

Overlay Control Surface

You can now control key workflow settings directly from the overlay:

• Mode selection (Dictate / Edit Text / Command)
• Prompt selection per mode
• AI Enhancement toggle (on/off)
• Actions menu for quick operations
• Settings shortcut (gear) to open Preferences instantly

Action Menus and More

• Reprocess last dictation
• Copy last transcription
• Undo AI processing on last transcription
• Improved action reliability and fallback behavior

Prompts and Advanced (Write/Edit Updates)

• Write/Edit mode controls are now consolidated into Prompts & Advanced for a cleaner workflow.
• Reduced mode confusion by centralizing prompt behavior and mode-specific controls.
• Navigation update: separate Write / Rewrite sidebar items were removed.
• These workflows now live under AI Enhancement settings as Edit Text mode.

Custom Prompt Profiles

• Added custom prompting support for both Dictate and Edit Text modes.
• You can create and manage multiple prompt profiles per mode.
• Active prompt can be selected quickly in the overlay, making prompt switching much faster during live use.

Prompt and Edit Text Workflow Improvements

• Clearer separation and naming for Dictate vs Edit Text workflows
• Better context behavior and prompt routing in Edit Text mode
• Improved provider/model sync behavior for Edit Text settings

Word Boosting

• Added stronger custom vocabulary boosting workflow for Parakeet models
• Improved boost controls and tuning behavior
• Better custom words UX and prioritization

Reliability and Stability

• Deterministic hotkey mode switching to avoid accidental processing on mode change
• Improved overlay processing-state behavior and cancellation handling
• Better model/provider handling and ASR improvements
• Improved audio/device edge-case handling
• Better Icon sizing for Non 26.0 macOS devices @moogman
• Fixed app freeze when USB microphone is plugged in during recording @JereSalo

Known Issues (macOS Sonoma)

• We are aware of multiple crashes on macOS Sonoma.
• These are related to newer UI elements that are not fully supported on Sonoma.
• If you need immediate stability, please update to macOS Sequoia (15.x).

Intel Note (Beta)

• Fixed an Intel launch/crash risk caused by architecture mismatch in the embedded MediaRemoteAdapter.framework.
• Intel support in this release should be treated as beta.
• If you see Intel-specific issues, please reach out on Discord: https://discord.gg/VUPHaKSvYV
• Or open a GitHub issue: https://github.com/altic-dev/FluidVoice/issues

FluidVoice v1.5.7-beta.2

FluidVoice v1.5.7-beta.2

Beta Notice

• This is a beta build and may be unstable.
• Please report any issues with logs.

Changes

• Fixed crash (SIGTRAP) during streaming transcription when custom vocabulary terms are configured.
• Vocabulary Boosting is now an opt-in toggle in Custom Dictionary (off by default).
• Text replacement (Instant Replacement) continues to work regardless of the toggle.

Help Us Improve

• Report issues here: https://github.com/altic-dev/FluidVoice/issues