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