FluidVoice vs Handy

FluidVoice

• Mac users who want free dictation that stays on the device
• AI text cleanup without a cloud account or API key
• Developers dictating prompts into terminals and code editors

Handy

• People who want free dictation that never uploads audio
• Dictating on Linux as well as macOS and Windows
• Developers who want a small codebase to fork and extend

FluidVoice

• Mac only for now: iPhone and Windows versions are listed as coming soon, with a waitlist.
• It requires macOS 15.0 or later, and Intel Macs are limited to the Whisper and Apple Speech models.
• Fluid Intelligence is a separate, privately maintained runtime and is not part of the open-source code.
• Choosing OpenAI, Groq or another cloud provider for enhancement sends text off the Mac.

Handy

• It transcribes microphone input only and cannot capture system audio from calls or videos.
• There is no live streaming transcription: Handy records a segment, then transcribes it, and recordings work best under 3 to 5 minutes.
• Spoken punctuation commands are not supported, and AI post-processing is an alpha feature that needs your own API key or a local model.
• There are no mobile apps; downloads cover macOS, Windows and Linux.

FluidVoice

System-wide dictation

Hold one global hotkey and speak, and the text is typed into any text field through macOS accessibility APIs. A live preview overlay shows words as they are recognized.

On-device speech models

Nemotron Speech 3.5, Parakeet, Cohere Transcribe, Apple Speech and Whisper models run locally. Language coverage depends on the model, from English only up to 99 languages with Whisper.

Fluid Intelligence

An optional local AI runtime, about a 3.5 GB download, runs the Fluid-1 model to strip filler, fix capitalization and format text with no cloud service or API key.

Write Mode and Command Mode

Write Mode drafts new text or rewrites a selection in any text field. Command Mode launches apps, runs shortcuts and triggers system actions by voice.

Per-app prompts

Assign different prompt sets to different apps so the tone follows the context, for example casual in Slack and formal in Mail.

Optional cloud AI enhancement

Post-processing can instead use OpenAI, Groq or a custom provider with your own API key, which is stored in the macOS Keychain.

Handy

Shortcut-driven dictation

Press a shortcut to start and stop recording, or hold it for push-to-talk, and the text is pasted into the app you are typing in. Shortcuts can be remapped in settings.

Local speech models

Choose from Parakeet, Whisper, Moonshine and other models that run on the device, with GPU acceleration when available. Parakeet V3 covers 25 European languages and Whisper 99+.

Optional AI post-processing

An experimental feature runs the transcript through a language model to fix grammar or reformat it, using a cloud provider key, an OpenAI-compatible local endpoint or Apple Intelligence.

Custom words

List names and jargon that are often misheard, and Handy corrects similar-sounding words to match. The docs describe this matching as imperfect.

Transcription history

Past transcriptions are kept with a timestamp and the original audio, and entries can be copied, starred or deleted. A limit setting controls how many are stored.

Command-line control

Flags such as --toggle-transcription and --cancel control a running instance, and --start-hidden launches Handy straight to the system tray.

FluidVoice

• FluidVoice$0

  The full Mac app with every speech model, Write and Command modes and optional Fluid Intelligence. GitHub Sponsors support is optional.

Handy

• Handy$0

  The full app for macOS, Windows and Linux with every local model. Donations and GitHub Sponsors are optional.