ABexit / ASR-LLM-TTS
This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three TTS models: CosyVoice, Edge-TTS, and pyttsx3
☆159Updated 2 weeks ago
Alternatives and similar repositories for ASR-LLM-TTS:
Users that are interested in ASR-LLM-TTS are comparing it to the libraries listed below
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆256Updated last month
- 实时STT,连接OpenAI接口/智谱AI(流式LLM)和GPT-SOVITS/Edge-TTS,通过网页的方式,进行跨网络的服务调用,实现实时对话的效果☆265Updated 5 months ago
- 低成本的简单基于live2d TTS文字转语音和大模型聊天的直播解决方案☆172Updated 5 months ago
- 基于 faster-whisper 的伪实时语音转写服务☆188Updated 3 months ago
- 【脱离复杂的环境配置和整合包,极简配置推理服务】从GPT-SoVITS项目里面提取出来的,纯粹的推理服务方案。☆218Updated 8 months ago
- 适用于 GPT-SoVITS 的api调用接口☆213Updated 9 months ago
- Step-by-step Jupyter notebook tutorials for ChatTTS☆122Updated 6 months ago
- A Bob plugin that calls self-deployed Cosyvoice service to achieve TTS.☆21Updated 4 months ago
- 一个用于CosyVoice的api接口项目☆88Updated 3 weeks ago
- 文本语料转训练集工具,txt转dataset☆79Updated 7 months ago
- CosyVoice在Windows环境下使用的版本☆505Updated 3 weeks ago
- AI虚拟伙伴Web版☆96Updated 2 months ago
- ☆298Updated 4 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☆150Updated last month
- 10000 chatTTS voices !chatTTS 音色库,再也不为音色抽卡烦恼啦。这是我第一个项目,熬夜龟速生产10000条音色并上传Github,给点鼓励呗哈!主域名:https://www.TTSlist.com 备用:http://ttslist.aiqb…☆145Updated 5 months ago
- Pseudo Streaming SenseVoice with Hotwords☆128Updated last month
- 官方推荐的 ChatTTS 最佳入门指南,整理 和汇总了常见问题和相关资源☆74Updated 5 months ago
- Build your own AI friend☆110Updated 2 weeks ago
- 基于中文文本情绪分析自动切换参考音频的 GPT-SoVITS 推理 Demo☆82Updated 9 months ago
- Simply animate your 2D waifu.☆92Updated 5 months ago
- Real time streaming talking head☆446Updated 7 months ago
- Sample GLM4V + ChatTTS AI assistant☆85Updated 6 months ago
- 百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,时延低至800ms,低配置也可运行,支持打断☆50Updated this week
- GraphRAG-Ollama-UI + GraphRAG4OpenWebUI 融合版(有gradio webui配置生成RAG索引,有fastapi提供RAG API服务)☆90Updated 3 months ago
- Bert-vits2转写和标注独立整合Webui,整合阿里FunAsr,必剪Asr以及Whisper大模型☆156Updated 5 months ago
- ChatTTS HTTP API☆49Updated 6 months ago
- AI桌宠2.2(网页端toklen白嫖国产大 模型服务器(glm4,kimi,deepseekv2),语音识别,屏幕识别自动发送,live2d 2.0和3.0模型,gpt-sovits语音,coysvoice语音,edge-tts语音(支持多语言音色),本地ollama模型无…☆78Updated 4 months ago
- 实时互动的GPT数字人☆318Updated last month
- 你是否曾经幻想过与自己的虚拟人交互?现在,使用PaddleAvatar,您可以将自己的图像、音频和视频转化为一个逼真的数字人视频,与其进行人机交互。 PaddleAvatar是一种基于PaddlePaddle深度学习框架的数字人生成工具,基于Paddle的许多套件,它可以…☆189Updated 3 months ago
- Inference Specialization☆372Updated 5 months ago