zaigie / FunSpeechLinks
开箱即用的本地私有化部署语音服务,快速搭建FunASR与CosyVoice2/3后端
☆80Updated 3 weeks ago
Alternatives and similar repositories for FunSpeech
Users that are interested in FunSpeech are comparing it to the libraries listed below
Sorting:
- 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。☆104Updated last year
- Unsloth框架在Windows平台微调训练Qwen2大模型,非WSL☆62Updated last year
- 一个中文语音转文字项目,封装自FireRedASR☆81Updated 10 months ago
- 基于SenseVoice的funasr版本进行的api发布,可以无缝对接oneapi☆90Updated last year
- This is a web-based intelligent dialogue program built using ASR, LLM, and TTS.☆24Updated last year
- 小智AI的MQTT+UDP服务器,支持后端Websocket程序动态负载均衡☆98Updated 7 months ago
- 一个用于CosyVoice的api接口项目☆332Updated 4 months ago
- This is a multi-character, ultra-personalized StoryTeller. It includes: 1) efficiently and accurately build multi-character voice library…☆58Updated 11 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)☆186Updated 10 months ago
- ☆119Updated last year
- Dify 新闻聚合插件-多平台新闻热榜获取☆52Updated 8 months ago
- Xiaozhi websocket protocol implemented by Golang, setup your own xiaozhi-server by routing requests to OpenAI Realtime API protocol such…☆39Updated 8 months ago
- 基于Linly-Talker数字人改版的教育系统,包含网课总结、数字人对话、Chatbot对话,项目可在autodl部署☆35Updated last year
- 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☆175Updated 7 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。☆93Updated 3 months ago
- Ollama 模型 Registry 镜像站 / 加速器,让 Ollama 从 ModelScope 魔搭 更快的 拉取 / 下载 模型。☆109Updated 9 months ago
- One command to run ChatTTS☆61Updated last year
- 一个简单的音频降噪工具,提高web UI界面和api接口☆44Updated last year
- RTC AIGC Demo☆238Updated 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☆430Updated last year
- 一个结合了ASR+LLM+TTS+监控的多功能AI机器人。支持所有以open ai为API调用格式的模型。支持LLM模型流式输出,以及对话打断、视频对话☆27Updated 9 months ago
- ☆33Updated 10 months ago
- 使用CHATTTS合成语音,使用FASTAPI作为API服务端,基于GFAST制作了管理系统,提供了音色管理和webui界面☆35Updated last year
- GodoAi Through deep integration with Olama, it has the ability to download models, have model conversations, manage knowledge bases, gene…☆34Updated last year
- 基于3D-Speaker的声纹识别API服务。用于识别小智设备说话人。☆98Updated 6 months ago
- 基于 faster-whisper 的伪实时语音转写服务☆234Updated 8 months ago
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆173Updated 11 months ago
- CosyVoice语音合成简易API☆14Updated last year
- 本地完整部署ASR(K2)-NLP(Rasa,Spacy)-LLM(Chatglm2)-TTS(Vits)☆150Updated 9 months ago
- 一个用于F5-TTS的api和webui项目☆65Updated last year