stt-streaming

Here is 1 public repository matching this topic...

soh-kaz / realtime-stt-kyutai

A high-performance, GPU-optimized real-time speech-to-text (STT) streaming server built with WebSocket support for multiple concurrent clients. This project leverages the Kyutai STT model and is optimized for NVIDIA RTX 4090 GPUs, providing low-latency transcription for audio streams.

python websocket speech-recognition speech-to-text stt realtime-audio mochi fastapi realtime-streaming kyutai stt-streaming

Updated Sep 19, 2025
Python

Add this topic to your repo

To associate your repository with the stt-streaming topic, visit your repo's landing page and select "manage topics."

Learn more