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
☆1,058Updated 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:
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆532Updated last year
- 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☆1,555Updated 4 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☆429Updated 11 months ago
- Step-by-step Jupyter notebook tutorials for ChatTTS☆172Updated last year
- Build your own AI friend☆713Updated 6 months ago
- Added vLLM support to IndexTTS for faster inference.☆941Updated last month
- 一个用于CosyVoice的api接口项目☆325Updated 3 months ago
- Pseudo Streaming SenseVoice with Hotwords☆406Updated 9 months ago
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,669Updated 3 months ago
- 适用于 GPT-SoVITS 的api调用接口☆323Updated last year
- 实时交互数字人，可自定义形象与音色，支持音色克隆，对话延迟低至3s。Real-time voice interactive digital human, customizable appearance and voice, supporting voice cloning,…☆1,175Updated this week
- 这是一款基于FunASR实现的说话人分离的GUI程序☆146Updated last week
- 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。☆563Updated 7 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。☆312Updated 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。☆1,263Updated last week
- A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization☆2,659Updated 2 weeks ago
- 使用vllm加速cosyvoice2的推理☆461Updated 7 months ago
- 基于 faster-whisper 的伪实时语音转写服务☆232Updated 7 months ago
- A Bob plugin that calls self-deployed Cosyvoice service to achieve TTS.☆39Updated last year
- CosyVoice在Windows环境下使用的版本☆750Updated last year
- 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）☆177Updated 9 months ago
- ☆237Updated 3 weeks 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…☆751Updated 4 months ago
- Sample Repository for the AlibabaCloud Bailian Speech SDK☆328Updated this 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☆171Updated 6 months ago
- AI虚拟伙伴Web版☆624Updated last week
- ☆372Updated last year
- 终极愿景：目标是创造一个全方位服务于用户全场景的 AI 全能管家AGI—“小粒”。除了不具备物理形态外，“小粒”将提供与远程视频通话中的真人几乎无异的体验，具备思考、情感交流、视觉、听觉以及模拟触觉反馈等能力，并能够游走在任何家庭、车辆等场景显示设备上自由与人交互。功能覆盖…☆140Updated 3 months ago
- A Python-based Xiaozhi AI for users who want the full Xiaozhi experience without owning specialized hardware.☆3,021Updated last month
- 每个人都能用的数字人☆1,791Updated last month