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
☆1,275Jun 3, 2026Updated 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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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，接入openClaw，真正的个人语音助手，时延低至800ms，Mac等低配置也可运行，支持打断☆1,759Apr 6, 2026Updated 4 months ago
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆542Oct 23, 2024Updated last year
- Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio…☆9,219Updated this week
- 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,…☆1,303Dec 18, 2025Updated 8 months ago
- Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.☆23,425May 25, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenA…☆20,151Updated this week
- This is a multi-character, ultra-personalized StoryTeller. It includes: 1) efficiently and accurately build multi-character voice library…☆66Feb 2, 2025Updated last year
- This is a web-based intelligent dialogue program built using ASR, LLM, and TTS.☆26Dec 3, 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☆435Dec 31, 2024Updated last year
- 1688找供应商 —— 结合用户需求与关键字查询对应的供应商及工厂信息 核心工具能力：1688供应商查询能力。用于查询1688平台上的供应商及工厂信息。 触发词：找供应商、查供应商、1688供应商、供应商信息、工厂信息、产业带查询。 不触发场景：找商品/选品 → 1688-…☆557May 7, 2026Updated 3 months ago
- 88生意通是1688线下B2B交易的得力帮手，一句话搞定全流程操作！无论您是卖家还是买家，只需一句指令，即可轻松完成交易单创建、签署、确认收货、退款等核心操作，全面支持账号状态查询、实名认证、绑卡及交易，让每一步交易流程更清晰、更可控。通过智能化交互，实现交易流程数字化，提…☆574Mar 27, 2026Updated 5 months ago
- 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.☆10,500Updated this week
- ASR_LLM_TTS前端项目☆15Dec 3, 2024Updated 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☆30Apr 15, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization☆3,129Dec 8, 2025Updated 8 months ago
- 1688 商家重点品圈选 —— 基于多维度商品评分智能识别值得重点运营的商品或搜索商品。 工具能力：五维度评分（销售贡献、流量效率、成长潜力、营销ROI、商品健康度），商品分层（S/A/B/C级），搜索商品。 触发词：重点品查看、圈选重点品、圈选运营商品、今日运营重点、选品…☆628May 11, 2026Updated 3 months ago
- 一个用于CosyVoice的api接口项目☆335Aug 31, 2025Updated last year
- Streaming ASR and TTS based on FastAPI+ sherpa-onnx☆225Nov 2, 2025Updated 10 months ago
- ☆19Jul 19, 2025Updated last year
- Pseudo Streaming SenseVoice with Hotwords☆470Jun 15, 2026Updated 2 months ago
- Real time interactive streaming digital human☆9,376Updated this week
- Open-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction.☆3,463Aug 17, 2026Updated 2 weeks ago
- Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime…☆14,581Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Lightning-responsive CosyVoice streaming API based on FastAPI.☆28Aug 17, 2026Updated 2 weeks ago
- A demo project for idempotent pipeline design, duplicate prevention, and retry-safe processing.☆288Mar 20, 2026Updated 5 months ago
- 使用vllm加速cosyvoice2的推理☆497Apr 26, 2025Updated last year
- A cautious, explainable AI-like text risk analyzer for local workflows and coding agents.☆441Aug 5, 2026Updated 3 weeks ago
- 异步语音对话组件。☆33Mar 13, 2025Updated last year
- GLM-4-Voice | 端到端中英语音对话模型☆3,229Dec 5, 2024Updated last year
- An MCP-based chatbot | 一个基于MCP的聊天机器人☆29,577Updated this week
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,977Feb 25, 2026Updated 6 months ago
- ☆33Feb 28, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 简单实现VAD+声纹锁+SenseVoice完成类语音实时转录的小项目☆42Sep 23, 2024Updated last year
- Sample Repository for the AlibabaCloud Bailian Speech SDK☆426Aug 14, 2026Updated 3 weeks ago
- Build your own AI friend☆792Jun 7, 2025Updated last year
- Real-time causal inference framework for Web Vitals optimization using streaming SCMs, public CrUX/PageSpeed field data, and auditable in…☆399Jul 2, 2026Updated 2 months ago
- ☆3,734Jul 31, 2026Updated last month
- 一个模块化，全过程可离线，低占用率的对话机器人/智能音箱☆162Mar 25, 2026Updated 5 months ago
- High-performance C++ voice interaction framework powered by ONNXRuntime and LLaMA.cpp. Features AEC, VAD, ASR, TTS, LLM, and MCP integrat…☆55Mar 5, 2026Updated 5 months ago