Stars
一个基于瑞芯微 SOC 的实验性项目，旨在实验 Rust 在嵌入式音视频与嵌入式视觉 AI 中的应用，将会实现完整的音视频采集、mp4离线录制、实时预览、WebRTC等 IPC 常用功能，以及基于 RKNN 部署视觉模型。
🚀 AI 全自动化视频生成员工 | Your First AIGC Coworker. Chat an Idea. Get a Film. 🦞
Native End-to-End Full-Duplex Spoken Language Model
ESP32-P4 WebRTC streaming, MQTT web control, CAN bus bridge, and ESP32-C3 servo robot demo.
Internet radio with FFT spectrum analyser
golang版本的小智后端服务，支持websocket和mqtt+udp协议，支持声纹识别/声音克隆/知识库/mcp远程调用/主动音频下发/openclaw等功能
Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.
ESP-Brookesia is a human-machine interaction development framework designed for AIoT devices.
Internet radio for AI Thinker ESP32-A1S and similar boards based on ESP-ADF audio libraries with web control, EQ and recording to SD card capabilities.
Enterprise-grade IoT platform powered by ThingLinks Engine. Supports MQTT / HTTP / CoAP / TCP / Modbus, rule engine, Visual display screen & multi-tenancy. Millions of connections per node.
A lightweight and fast C++ library for building MQTT clients and brokers, with support for QoS, authentication, security, persistence, and user/session management.
一个基于 Sherpa-ONNX 的高性能语音识别服务，支持实时VAD（语音活动检测）、多语言语音识别和声纹识别功能。
**VoiceLint** is a high-performance C++ pipeline for post-processing automatic speech recognition (ASR) results. It corrects raw ASR transcripts and generates structured summaries using lightweight…
一个连接astrbot和open llm vtuber的插件
Chat UI in graph 🌲. Unlike traditional chat UIs, users don’t need to delete messages to explore different responses—they can simply create new branches.
Streaming ASR and TTS based on FastAPI+ sherpa-onnx
Pure Javascript ChatGPT demo based on OpenAI API
Access your device's terminal from anywhere via the web.
✨✨[NeurIPS 2025] VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model