{"id":18185275,"url":"https://github.com/theboringhumane/echoOLlama","last_synced_at":"2025-04-02T00:31:44.349Z","repository":{"id":260730424,"uuid":"882025783","full_name":"theboringhumane/echoOLlama","owner":"theboringhumane","description":"🦙 echoOLlama: A real-time voice AI platform powered by local LLMs. Features WebSocket streaming, voice interactions, and OpenAI API compatibility. Built with FastAPI, Redis, and PostgreSQL. Perfect for private AI conversations and custom voice assistants. ","archived":false,"fork":false,"pushed_at":"2024-11-09T11:51:02.000Z","size":8598,"stargazers_count":97,"open_issues_count":2,"forks_count":4,"subscribers_count":3,"default_branch":"openai","last_synced_at":"2025-03-28T20:46:04.198Z","etag":null,"topics":["agent","docker","docker-compose","fastapi","lgm","llama","llama3","llm","multimodel-large-language-model","ollama","openai","realtime-api"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/theboringhumane.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-11-01T18:12:51.000Z","updated_at":"2025-03-23T01:29:39.000Z","dependencies_parsed_at":"2024-12-03T16:34:23.545Z","dependency_job_id":"55ca7b85-3447-4868-9447-d16e41bb5eea","html_url":"https://github.com/theboringhumane/echoOLlama","commit_stats":null,"previous_names":["iamharshdev/ollamagate","iamharshdev/echoollama","fofsinx/echoollama","theboringhumane/echoollama"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theboringhumane%2FechoOLlama","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theboringhumane%2FechoOLlama/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theboringhumane%2FechoOLlama/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theboringhumane%2FechoOLlama/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/theboringhumane","download_url":"https://codeload.github.com/theboringhumane/echoOLlama/tar.gz/refs/heads/openai","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246481005,"owners_count":20784458,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","docker","docker-compose","fastapi","lgm","llama","llama3","llm","multimodel-large-language-model","ollama","openai","realtime-api"],"created_at":"2024-11-02T23:00:22.640Z","updated_at":"2025-04-02T00:31:44.338Z","avatar_url":"https://github.com/theboringhumane.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🦙 `echoOLlama`: Reverse-engineered OpenAI’s [Realtime API]\n\u003e 🌟 Talk to your local LLM models in human voice and get responses in realtime!\n\n![🦙 EchoOLlama Banner](https://github.com/user-attachments/assets/d2422917-b03a-48aa-88c8-d40f0884bd5e)\n\n\u003e ⚠️ **Active Development Alert!** ⚠️\n\u003e\n\u003e We're cooking up something amazing! While the core functionality is taking shape, some features are still in the oven. Perfect for experiments, but maybe hold off on that production deployment for now! 😉\n\n## 🎯 What's `echoOLlama`?\n`echoOLlama` is a cool project that lets you talk to AI models using your voice, just like you'd talk to a real person! 🗣️\n\nHere's what makes it special:\n\n- 🎤 You can speak naturally and the AI understands you\n- 🤖 It works with local AI models (through Ollama) so your data stays private\n- ⚡ Super fast responses in real-time\n- 🔊 The AI talks back to you with a natural voice\n- 🔄 Works just like OpenAI's API but with your own models\n\nThink of it like having a smart assistant that runs completely on your computer. You can have natural conversations with it, ask questions, get help with tasks - all through voice! And because it uses local AI models, you don't need to worry about your conversations being stored in the cloud.\n\nPerfect for developers who want to:\n- Build voice-enabled AI applications\n- Create custom AI assistants\n- Experiment with local language models\n- Have private AI conversations\n\n\n### 🎉 What's Working Now:\n\n![🦙 EchoOLlama Banner](https://github.com/user-attachments/assets/5ce20abf-6982-4b6b-a824-58f7d91ef7cd)\n\n- ✅ Connection handling and session management\n- ✅ Real-time event streaming\n- ✅ Redis-based session storage\n- ✅ Basic database interactions\n- ✅ OpenAI compatibility layer\n- ✅ Core WebSocket infrastructure\n\n### 🚧 On the Roadmap:\n- 📝 Message processing pipeline (In Progress)\n- 🤖 Advanced response generation with client events\n- 🎯 Function calling implementation with client events\n- 🔊 Audio transcription service connection with client events\n- 🗣️ Text-to-speech integration with client events\n- 📊 Usage analytics dashboard\n- 🔐 Enhanced authentication system\n\n## 🌟 Features \u0026 Capabilities\n\n### 🎮 Core Services\n- **Real-time Chat** 💬\n  - Streaming responses via websockets\n  - Multi-model support via Ollama\n  - Session persistence\n  - 🎤 Audio Transcription (FASTER_Whisper)\n  - 🗣️ Text-to-Speech (OpenedAI/Speech)\n\n- **Coming Soon** 🔜\n  - 🔧 Function Calling System\n  - 📊 Advanced Analytics\n\n### 🛠️ Technical Goodies\n- ⚡ Lightning-fast response times\n- 🔒 Built-in rate limiting\n- 📈 Usage tracking ready\n- ⚖️ Load balancing for scale\n- 🎯 100% OpenAI API compatibility\n\n\n\n## 🏗️ System Architecture\n\n\u003ca href='https://excalidraw.com/#json=FbCQY2ha_EX6w2CjqK6Mr,lWhsDsgEPXLsSELFBzBxqw' target='_blank'\u003e\n\u003cimg src='https://preview.redd.it/ollamagate-open-sourced-openai-v0-isuuo6mh7uyd1.png?width=2602\u0026format=png\u0026auto=webp\u0026s=d497e1da5cd93874126e826ec3990a23e5339faa' alt='echoOLlama' /\u003e\n\u003c/a\u003e\n\n\u003e Click on the image to view the interactive version on Excalidraw!\n\n## 💻 Tech Stack Spotlight\n### 🎯 Backend Champions\n- 🚀 FastAPI - Lightning-fast API framework\n- 📝 Redis - Blazing-fast caching \u0026 session management\n- 🐘 PostgreSQL - Rock-solid data storage\n\n### 🤖 AI Powerhouse\n- 🦙 Ollama - Local LLM inference\n- 🎤 faster_whisper - Speech recognition (coming soon)\n- 🗣️ OpenedAI TTS - Voice synthesis (coming soon)\n\n## 🚀 Get Started in 3, 2, 1...\n\n1. **Clone \u0026 Setup** 📦\n```bash\ngit clone https://github.com/iamharshdev/EchoOLlama.git\ncd EchoOLlama\npython -m venv .venv\nsource .venv/bin/activate  # or `.venv\\Scripts\\activate` on Windows\npip install -r requirements.txt\n```\n\n2. **Environment Setup** ⚙️\n```bash\ncp .env.example .env\n# Update .env with your config - check .env.example for all options!\nmake migrate # create db and apply migrations\n```\n\n3. **Launch Time** 🚀\n```bash\n# Fire up the services\ndocker-compose up -d\n\n# Start the API server\nuvicorn app.main:app --reload\n```\n\n## 🤝 Join the EchoOLlama Family\nGot ideas? Found a bug? Want to contribute? Check out our [CONTRIBUTING.md](CONTRIBUTING.md) guide and become part of something awesome! We love pull requests! 🎉\n\n## 💡 Project Status Updates\n- 🟢 **Working**: Connection handling, session management, event streaming\n- 🟡 **In Progress**: Message processing, response generation\n- 🔴 **Planned**: Audio services, function calling, analytics\n\n## 📜 License\nMIT Licensed - Go wild! See [LICENSE](LICENSE) for the legal stuff.\n\n---\n*Built with 💖 by the community, for the community*\n\n*PS: Star ⭐ us on GitHub if you like what we're building!*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftheboringhumane%2FechoOLlama","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftheboringhumane%2FechoOLlama","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftheboringhumane%2FechoOLlama/lists"}