Voice dictation often trades convenience for cloud processing. Hex takes a different route: speech recognition happens on the device, so the same shortcut can enter text across apps without sending routine dictation audio to a transcription service.
AI Audio2026
Hex
Turns speech into text in whichever app is active: hold a shortcut, speak, and release. Transcription runs locally after the speech model is downloaded, keeping routine dictation on your device.
Introduction
More Items
AI Model2026
Generates speech from text and can clone a voice from a reference recording without fine-tuning. The 601M-parameter model supports 23 languages, though output quality varies by language.
AI Model2026
Handles text and speech input, producing text, speech, or both for streaming voice interaction, multilingual audio tasks, and spoken tool calls. Its 2B-parameter size targets local and edge use, not complex multi-step reasoning.
