Launched this week
Sonora
Local TTS, STT & dictation for Windows
5 followers
Local TTS, STT & dictation for Windows
5 followers
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.
Nice direction. Curious—what pushed you to build a local-first speech stack instead of relying on cloud APIs like most tools do today?
@aryan787544 It came from my own frustration. I wanted speech recognition that worked instantly, protected user privacy, and didn't rack up API costs as usage grew.
By running the speech stack locally, Sonora offers lower latency, works even with limited or no internet, and keeps audio on the user's device whenever possible.
Cloud APIs are still excellent for many use cases, but I wanted to prove that a local-first experience can be just as capable while being faster, more private, and more cost-effective in the long run.