ABexit / ASR-LLM-TTSLinks
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
☆764Updated 3 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:
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆445Updated 7 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，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断☆1,248Updated 2 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☆387Updated 5 months ago
- 一个用于CosyVoice的api接口项目☆279Updated 4 months ago
- 实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, su…☆945Updated 2 months ago
- Pseudo Streaming SenseVoice with Hotwords☆280Updated 2 months ago
- Build your own AI friend☆613Updated 4 months ago
- 适用于 GPT-SoVITS 的api调用接口☆280Updated last year
- Step-by-step Jupyter notebook tutorials for ChatTTS☆158Updated 11 months ago
- 基于 faster-whisper 的伪实时语音转写服务☆215Updated last month
- ☆1,133Updated 3 weeks ago
- 使用vllm加速cosyvoice2的推理☆295Updated last month
- 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。☆414Updated 2 weeks ago
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,002Updated 2 months ago
- 每个人都能用的数字人☆1,447Updated 2 weeks ago
- CosyVoice在Windows环境下使用的版本☆682Updated 6 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。☆288Updated last year
- 一个基于小智、xiaozhi-server的Android、IOS语音对话应用,支持实时语音交互和文字对话。现在是flutter版本，打通IOS、Android端。请同志们动动小手，点点小星星，予以鼓励。☆675Updated last week
- AI虚拟伙伴Web版☆450Updated last month
- A Bob plugin that calls self-deployed Cosyvoice service to achieve TTS.☆37Updated 9 months ago
- python版本的小智ai，主要帮助那些没有硬件却想体验小智功能的人,如果可以请点个小星星！☆1,623Updated last week
- 一个超轻量级、可以在移动端实时运行的数字人模型☆1,936Updated 2 months ago
- A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization☆2,066Updated last week
- 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☆113Updated 2 months ago
- Multilingual Voice Understanding Model☆5,744Updated 2 months ago
- ☆359Updated 10 months ago
- The simplest and lowest-cost AI integration solution. If you like this project, please give it a Star~ | 最简单、最低成本的AI接入方案。喜欢本项目的话点个 Star 吧…☆703Updated 2 weeks ago
- Awesome Digital Human☆1,713Updated 4 months ago
- 本地完整部署ASR(K2)-NLP(Rasa,Spacy)-LLM(Chatglm2)-TTS(Vits)☆138Updated last month
- The fastest digital human algorithm, now on your desktop.☆517Updated 5 months ago