Dictato turns speech into text on your Mac, providing fast, private dictation capabilities. The app lives in your menu bar and is always ready to transcribe your speech using on-device machine learning models. It works with virtually any macOS application where you can type, inserting text directly at your cursor position.

Dictato offers three transcription engines with different strengths: Parakeet is NVIDIA's open-source ASR model optimized for speed and accuracy, supporting 25 European languages with a model size of approximately 2.3 GB. Whisper is OpenAI's speech recognition model supporting 99 languages with a smaller model size of around 600 MB. Apple SpeechAnalyzer is Apple's built-in engine available on macOS 26 and later that requires no model download.

The app uses macOS accessibility features to insert transcribed text directly at your cursor position in any application. Under the hood, Dictato leverages Apple Silicon's Neural Engine for fast inference, processing audio locally in real time with latency as low as 80 milliseconds. The transcription engine runs entirely on your Mac's hardware, with audio processed locally and discarded immediately after processing.

Dictato enables users to write 3x faster by speaking at 150 WPM instead of typing at 40 WPM. It eliminates the 60-second timeout limitation of Mac's built-in dictation, allowing users to dictate for as long as needed. The app works everywhere including Gmail, Slack, VS Code, Notion, Pages, and countless other macOS applications.

Dictato is built for writers, developers, and professionals who need fast, private dictation. It's suitable for sensitive use cases like legal professionals dictating confidential notes, medical practitioners documenting patient information, journalists protecting sources, or anyone who values privacy. The app requires macOS Sonoma (macOS 14) or later on Apple Silicon Macs.