lukeewin / ASR_LLM_TTSLinks
This is a web-based intelligent dialogue program built using ASR, LLM, and TTS.
☆22Updated 9 months 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
Sorting:
- ASR_LLM_TTS前端项目☆14Updated 9 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。☆98Updated last year
- CosyVoice语音 合成简易API☆12Updated 10 months ago
- 一个用于CosyVoice的api接口项目☆308Updated this week
- 异步语音对话组件。☆26Updated 5 months ago
- 基于SenseVoice的funasr版本进行的api发布,可以无缝对接oneapi☆73Updated 11 months ago
- 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☆413Updated 8 months ago
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆498Updated 10 months ago
- CosyVoice2 功能扩充(预训练音色推理/3s极速复刻/自然语言控制/自动识别/音色模型保存/API)☆162Updated 5 months ago
- 一个中文语音转文字项目,封装自FireRedASR☆68Updated 6 months ago
- 小智AI的MQTT+UDP服务器,支持后端Websocket程序动态负载均衡☆63Updated 3 months ago
- Streaming ASR and TTS based on FastAPI+ sherpa-onnx☆145Updated 4 months ago
- 这是一款基于FunASR实现的说话人分离的GUI程序☆120Updated last month
- Added vLLM support to IndexTTS for faster inference.☆472Updated this week
- ☆367Updated last year
- 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☆184Updated last year
- Pseudo Streaming SenseVoice with Hotwords☆343Updated 5 months ago
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆170Updated 6 months ago
- ☆49Updated last year
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆43Updated 10 months ago
- 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。☆84Updated 2 months ago
- ☆30Updated 6 months ago
- 使用vllm加速cosyvoice2的推理☆406Updated 4 months ago
- 小智同学测试工具(websocket)☆43Updated 6 months ago
- Fast-TTS 是一个基于异步框架的文本到语音转换(TTS)生成器项目。该项目利用了异步编程技术来高效处理请求和响应,实现了快速、秒级的流式生成长文本语音播放服务。Fast-TTS 可以快速地将长文本转换为语音流,并实时播放,适用于多种应用场景,如语音合成、智能助手、内容…☆44Updated 9 months ago
- Bert-VITS2项目bug多且教程不友好。本proj尽可能修复了Bert-vits2项目的bug,并且可一键启动训练。仅需50条目标说话人语音,获得稳定、快速的TTS模型。☆64Updated 2 weeks ago
- 基于 faster-whisper 的伪实时语音转写服务☆226Updated 4 months ago
- 小智机器人服务端☆18Updated 5 months ago
- 本地完整部署ASR(K2)-NLP(Rasa,Spacy)-LLM(Chatglm2)-TTS(Vits)☆148Updated 4 months ago
- 基于SparkTTS、OrpheusTTS等模型,提供高质量中文语音合成与声音克隆服务。☆513Updated 3 months ago