Handy vs Whispering

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

Whispering

• People who want dictation software whose code they can audit
• Users willing to add their own API keys and pay providers directly
• Offline dictation with on-device models on Mac and Linux

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.

Whispering

• Cloud transcription and AI transformations need your own provider API keys, and the provider bills the usage.
• The macOS download is for Apple Silicon only, and Windows builds include just the English-only Parakeet engine for local transcription.
• It is built for short dictation; the site suggests a dedicated recording app for long sessions.
• The browser version has no system-wide shortcuts, and the project's README on GitHub says the hosted web build is no longer being republished.

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.

Whispering

Shortcut-driven dictation

Press a keyboard shortcut, speak, and the text is copied and pasted where the cursor is. The recording shortcut can be changed in settings.

Voice-activated mode

With voice activity detection turned on, recording starts when you begin speaking and stops after a short pause, so no key has to be held.

Cloud providers with your own keys

Audio goes straight from the device to Groq, OpenAI or ElevenLabs under your own API key, with no Whispering server in between. Groq also has a free tier.

Local transcription engines

Version 7.11.0 bundles Parakeet, Moonshine and Whisper C++ for on-device transcription, with Whisper C++ covering 65 languages. Speaches, a local transcription service, is also supported.

AI transformations

Chain steps that send the transcript to a model from OpenAI, Anthropic, Google Gemini, Groq or any OpenAI-compatible endpoint, or run find-and-replace, to fix grammar, translate or summarize.

Recordings stored on the device

Recordings, transcripts and transformation settings are kept locally. Anonymized usage analytics are collected through Aptabase and can be switched off in settings.

Handy

• Handy$0

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

Whispering

• Whispering$0

  The full desktop and browser app. Cloud providers bill usage to your own API key: the site lists Groq at $0.02 to $0.04 per hour of audio.