Google's free hands-free Android control app. Processes commands mostly on-device, and works fully offline once you download a language pack.

MIT-licensed Linux voice typing on whisper.cpp with optional AI post-processing via local llama.cpp or cloud APIs. 99+ languages, no GPU needed.

Free MIT offline transcription for Mac, Windows, and Linux with speaker diarization, batch processing, and exports to SRT, VTT, DOCX, PDF and more.

Local Whisper and Parakeet transcription free forever on Mac, plus an iOS keyboard. Pro adds managed cloud models at $8.33/month billed annually.

Free open-source transcription that runs in the browser or inside the Epicenter desktop app, with local GGUF models or your own cloud provider keys.

Native Mac app that transcribes audio and video files locally with Whisper. Free tier included; Pro is a one-time €59 with batch processing and speaker labels.

Free dictation in Android's Gboard keyboard with downloadable offline language packs. Assistant voice typing needs a Pixel 6 or newer.

Free MIT-licensed offline transcription and translation for Mac, Windows, and Linux. Handles files, videos, YouTube links, and live microphone input.

Apple's built-in dictation runs fully on-device on Apple Silicon with no time limit and no cost. WWDC 2026 added on-device auto-punctuation and formatting.

Apple's built-in voice control for Mac, iPhone, and iPad. Works fully offline, costs nothing, and gains natural language input via Apple Intelligence in 2026.

LGPL Python framework for writing custom speech recognition grammars, with a single API across Dragon, Windows Speech Recognition, Kaldi, and Pocket Sphinx.

Comprehensive AAC and environmental control software for Windows, supporting eye gaze, switch, touch, and pointer access. Around £550 with a 60-day free trial.

On-device dictation for Mac, Windows, and iOS with selectable Whisper models, scriptable modes, and a $249.99 lifetime licence. Free tier is uncapped.

Nuance's Windows dictation software, still sold as a $699.99 one-time licence. Mac, Home, and mobile editions have all been discontinued.

The legacy Windows voice control tool, deprecated December 2023 and replaced by Voice Access on Windows 11 22H2+. No longer developed.

Free hands-free computer control with voice, noise recognition, and eye tracking, scriptable in Python. The platform most voice coding setups are built on.

Hackable offline Linux dictation built on VOSK. A single Python script with no daemon, configured by writing Python rather than clicking settings.

Free MIT-licensed dictation for Mac and Windows combining local Whisper transcription with Ollama for AI cleanup. Runs entirely offline.

Free cross-platform dictation app running Whisper or NVIDIA Parakeet locally, or cloud models with your own keys. MIT licensed, no telemetry.

Free MIT-licensed dictation for Mac, Windows, and Linux running Whisper or Parakeet fully offline. No account, no subscription, no cloud.

Free libre voice control for Linux, running locally. Built for people who can't otherwise use a computer, and for avoiding hand strain.

Free AGPL Linux dictation running whisper.cpp, Whisper, or VOSK entirely offline, with GPU acceleration and system tray integration across X11 and Wayland.

Free voice programming toolkit built on Dragonfly with prebuilt commands for 13+ languages and major IDEs. Needs Dragon, Kaldi, or Windows Speech Recognition.

Free Mac dictation with AI cleanup running entirely on-device. No account, no word cap, no paid tier. Apple Silicon only.

Open-source macOS dictation that runs Whisper, Parakeet, and Cohere models entirely on-device. One-time $29 for a single Mac, no subscription.

Mac and iPhone dictation that runs offline on Apple Silicon or free with your own API keys. utterPRO adds managed frontier models for $5/month.