Sonora
Local TTS, STT & dictation for Windows
Start new thread

Sonora - Local TTS, STT & dictation for Windows

by•
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.

Add a comment

Replies

Best
Maker
📌
Hey Product Hunt 👋 I’m the maker of Sonora. I got tired of cloud TTS/STT for everyday work—latency, cost, and sending voice off-device. So I built a Windows app that keeps speech local: 🎙️ Multi-engine TTS (studio UI + custom voices) 📝 STT with optional speaker diarization ⌨️ Global dictation — hotkey into any text field 🔌 Localhost API for scripts & agents After the first model download, it runs offline. GPU helps a lot; CPU still works. Landing: Would love feedback from folks who care about local AI / privacy / agent tooling. What’s the first thing you’d try—dictation, TTS, or the API?