Gager-Git-life / llm_stsLinks
A real-time voice conversation system based on WebSocket and LLM, integrating Automatic Speech Recognition (ASR), Large Language Model conversation (LLM), and Text-to-Speech (TTS) capabilities.
☆17Updated 4 months ago
Alternatives and similar repositories for llm_sts
Users that are interested in llm_sts are comparing it to the libraries listed below
Sorting:
- [真诚套壳]东半球最强的套壳数字人系统，前后端分离，可对接硅基、飞影、闪剪、壹定开放平台等所有市面上的数字人API接口，开箱即用，star交个朋友。☆77Updated 7 months ago
- 如果想体验小智项目，或者开发server端测试的同志，可以使用这个web端damo 体验下。 语音端已经完成，文字端完成，可以语音加文字输出。 等迭代慢慢完善。欢迎PR☆124Updated 3 weeks ago
- 虾哥的小智 AI 聊天机器人（XiaoZhi AI Chatbot）- python客户端☆92Updated last month
- TalkX，一个开源的AI大模型聊天平台，支持编程插件、小智设备连接使用。☆76Updated 3 weeks ago
- 使用vllm加速cosyvoice2的推理☆344Updated 2 months ago
- 通过此代码可以免训练模型并通过轻量级服务器定制数字人形象☆104Updated last year
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆462Updated 8 months ago
- 洛曦 数字人视频播放器，带HTTP API，使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk，也可以用于播放本地视频☆165Updated 8 months ago
- 阿里SenseVoice的fastpi封装，采用onnx发布，体积更小，附带量化模型，支持GPU。支持从URL文件进行语音识别。☆86Updated 9 months ago
- 在DH_live项目基础上修改，添加webui界面☆61Updated 2 months ago
- ☆25Updated 4 months ago
- 将Wav2Lip和GFPGAN进行结合实现高清数字人说话视频☆31Updated 3 weeks ago
- Pseudo Streaming SenseVoice with Hotwords☆297Updated 3 months ago
- 使用 FastAPI、Streamlit本地部署ChatTTS文本转语音模型，并通过 Docker Compose 进行容器化部署。☆27Updated 9 months ago
- 小智同学测试工具(websocket)☆43Updated 4 months ago
- XiaoZhi AI Voicebot Android Demo☆46Updated 3 months ago
- 一个用于CosyVoice的api接口项目☆291Updated 5 months ago
- funasr语音转文字的简单api版本，funasr+fastapi，方便部署在服务器上☆12Updated 10 months ago
- This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice…☆809Updated 3 months ago
- 小智AI的MQTT+UDP服务器，支持后端Websocket程序动态负载均衡☆45Updated last month
- 本地完整部署ASR(K2)-NLP(Rasa,Spacy)-LLM(Chatglm2)-TTS(Vits)☆142Updated 2 months ago
- 一个模块化，全过程可离线，低占用率的对话机器人/智能音箱☆88Updated 3 months ago
- ☆224Updated 4 months ago
- 获取bilibili直播弹幕，使用WebSocket协议☆36Updated last year
- 基于FunASR官方Demo修改的WS服务端，配合FastAPI提供HTTP服务，可以在浏览器中进行实时ASR测试☆23Updated 5 months ago
- ☆75Updated last week
- The fastest digital human algorithm, now on your desktop.☆530Updated 2 weeks ago
- 优化wav2lip的执行步骤，将头脸分离、嘴型替换、回补背景三个步骤分离，添加gfpgan强化面部功能，实现提前解帧，流式循环处理，对接obs☆73Updated 6 months ago
- 数字人训练☆18Updated last year
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆72Updated 2 months ago