Speech To Speech
Low-latency speech-to-speech pipeline
About
A low-latency, fully modular voice-agent pipeline: VAD -> STT -> LLM -> TTS, exposed through the core OpenAI Realtime GA event set over WebSocket and WebRTC. Every component is swappable. The LLM slot speaks OpenAI-compatible protocols, so you can point it at a hosted provider, at HF Inference Providers, or at a vLLM or llama.cpp server on your own hardware for a fully local, fully open stack.
Open Source Health
- Stars
- 13,184
- Forks
- 1,664
- License
- Apache-2.0
- Last commit
- 1 months ago
Resources & Links
Related Categories
Vendor
Hugging Face
Quick Links
Open Source
Stars
13.2K
Forks
1.7K
Contributors
0
Open Issues
105
More by Hugging Face
Related Products
Rclip
Semantic photo search for the command line
Top category match
ChineseNER
A neural network model for Chinese named entity recognition
Top category match
Head Pose Estimation
Realtime human head pose estimation with ONNXRuntime and OpenCV.
Top category match
Video Subtitle Extractor
视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
Top category match
U 2 Net
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Top category match