Sonora is a powerful Windows desktop speech studio designed for makers and developers who prioritize privacy and local control. Operating entirely offline after the initial model downloads, Sonora eliminates the need for daily cloud API usage, ensuring that your voice data never gets shipped to a SaaS provider.
Built with versatility in mind, Sonora features a multi-engine local text-to-speech (TTS) studio UI complete with custom voices, robust speech-to-text (STT) capabilities featuring optional speaker labels, and convenient global dictation via hotkeys for voice typing into any focused Windows field. Additionally, it offers a localhost HTTP API, allowing custom scripts and AI agents to seamlessly call TTS and STT directly on your local machine. Whether you are running it on a dedicated GPU or relying on a CPU, Sonora provides a flexible, privacy-first voice solution for Windows.
No. Once you download the required models, Sonora runs fully offline without needing a cloud API for daily use.
Yes, Sonora features global dictation via hotkeys, enabling voice typing directly into any focused Windows field.
Yes, Sonora includes a localhost HTTP API so that local scripts and AI agents can execute TTS and STT operations directly on your machine.
Sonora is GPU-friendly and is also designed to work smoothly on a standard CPU.
0 community reviews for Sonora
Help the community by sharing your experience. Your review helps others make better decisions.
Indie hacker building AI products
