Sonora
Local TTS, STT & dictation for Windows
4
Product Hunt Upvotes
Jul 24, 2026
Launch Date
3d ago
First Tracked
About
AI Summary
Sonora is an offline Windows desktop speech studio that offers multi-engine text-to-speech (TTS) and speech-to-text (STT) capabilities, complete with a user-friendly interface and customizable voices, while ensuring user privacy by avoiding cloud services. It features global dictation, hotkey voice typing, and a localhost HTTP API for integration with scripts and AI agents, making it suitable for developers and creators.
Sonora is a Windows desktop speech studio that runs fully offline after models download, no cloud API for daily use. • Multi-engine local TTS with a studio UI and custom voices • Speech-to-text with optional speaker labels • Global dictation: hotkey voice typing into any focused Windows field • Localhost HTTP API so scripts and AI agents can call TTS/STT on your machine GPU-friendly, works on CPU too. Privacy-first voice for makers who don’t want every utterance shipped to a SaaS.
Tags