Unified Voice STT/TTS Server

tom_doerr · x · 2026-07-19

Sayna is a high-performance, real-time voice processing server written in Rust. It provides unified Speech-to-Text (STT) and Text-to-Speech (TTS) services, exposing them via WebSocket and REST APIs.

The project supports integration with multiple voice vendors; screenshots show coverage for Deepgram, ElevenLabs, Google, and Azure. It is positioned as a unified voice layer for upstream applications or AI agents.

Original post →

More from Apps

Apps channel →