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
☆1,628Jul 31, 2025Updated 7 months ago
Alternatives and similar repositories for bailing
Users that are interested in bailing are comparing it to the libraries listed below
Sorting:
- 本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.☆8,943Updated this week
- A Python-based Xiaozhi AI for users who want the full Xiaozhi experience without owning specialized hardware.☆3,231Jan 7, 2026Updated 2 months ago
- 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☆180Jun 7, 2025Updated 9 months ago
- An MCP-based chatbot | 一个基于MCP的聊天机器人☆24,900Updated this week
- 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。☆1,410Feb 10, 2026Updated last month
- This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice…☆1,145Mar 1, 2025Updated last year
- Build your own AI friend☆744Jun 7, 2025Updated 9 months ago
- A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity…☆15,243Mar 12, 2026Updated last week
- Multilingual Voice Understanding Model☆7,724Dec 30, 2025Updated 2 months ago
- 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,…☆1,221Dec 18, 2025Updated 3 months ago
- 小智ESP32的Java企业级管理平台，提供设备监控、音色定制、角色切换和对话记录管理的前后端及服务端一体化解决方案☆1,165Feb 26, 2026Updated 3 weeks ago
- Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.☆20,038Mar 16, 2026Updated last week
- 小智同学测试工具(websocket)☆46Feb 20, 2025Updated last year
- ☆242Nov 25, 2025Updated 3 months ago
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,807Feb 25, 2026Updated 3 weeks ago
- Real time interactive streaming digital human☆7,234Feb 24, 2026Updated 3 weeks ago
- A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization☆2,836Dec 8, 2025Updated 3 months ago
- GLM-4-Voice | 端到端中英语音对话模型☆3,152Dec 5, 2024Updated last year
- 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☆434Dec 31, 2024Updated last year
- 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。☆95Oct 16, 2025Updated 5 months ago
- Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime…☆10,947Updated this week
- ☆4,620Mar 16, 2026Updated last week
- 一个用于CosyVoice的api接口项目☆337Aug 31, 2025Updated 6 months ago
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆539Oct 23, 2024Updated last year
- Open-source framework for conversational voice AI agents☆10,285Updated this week
- Silero VAD: pre-trained enterprise-grade Voice Activity Detector☆8,518Mar 8, 2026Updated 2 weeks ago
- A generative speech model for daily dialogue.☆38,938Jan 18, 2026Updated 2 months ago
- Pseudo Streaming SenseVoice with Hotwords☆437Mar 13, 2025Updated last year
- Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key☆10,317Dec 12, 2025Updated 3 months ago
- ☆204Sep 24, 2024Updated last year
- Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LL…☆3,182Feb 10, 2026Updated last month
- SOTA Open Source TTS☆28,614Updated this week
- Streaming ASR and TTS based on FastAPI+ sherpa-onnx☆195Nov 2, 2025Updated 4 months ago
- 每个人都能用的数字人☆1,883Nov 8, 2025Updated 4 months ago
- ✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction☆2,496Mar 28, 2025Updated 11 months ago
- FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data process…☆27,405Updated this week
- 适用 于 NAS、路由器、树莓派等轻量级设备的 xiaozhi-esp32 服务端☆35Feb 27, 2026Updated 3 weeks ago
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆700Mar 12, 2026Updated last week
- ☆3,251Dec 19, 2025Updated 3 months ago