{"id":28255559,"url":"https://github.com/extrawest/voice_to_voice_communication_assistant","last_synced_at":"2026-01-20T16:26:40.584Z","repository":{"id":293483804,"uuid":"984178674","full_name":"extrawest/voice_to_voice_communication_assistant","owner":"extrawest","description":"A scalable voice assistant implementation using LiveKit for real-time communication, with custom Speech-to-Text (STT) and Text-to-Speech (TTS) integrations using local APIs.","archived":false,"fork":false,"pushed_at":"2025-06-13T17:16:35.000Z","size":17,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-16T15:25:46.644Z","etag":null,"topics":["ai","livekit","llm","ollama","openai","python","stt","tts"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/extrawest.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"zenodo":null}},"created_at":"2025-05-15T14:13:48.000Z","updated_at":"2025-06-13T17:16:38.000Z","dependencies_parsed_at":"2025-05-15T15:47:30.710Z","dependency_job_id":"f4df035c-fff6-4dc0-a15d-9785727f1430","html_url":"https://github.com/extrawest/voice_to_voice_communication_assistant","commit_stats":null,"previous_names":["extrawest/voice_to_voice_communication_assistant"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/extrawest/voice_to_voice_communication_assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/extrawest%2Fvoice_to_voice_communication_assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/extrawest%2Fvoice_to_voice_communication_assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/extrawest%2Fvoice_to_voice_communication_assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/extrawest%2Fvoice_to_voice_communication_assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/extrawest","download_url":"https://codeload.github.com/extrawest/voice_to_voice_communication_assistant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/extrawest%2Fvoice_to_voice_communication_assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28607035,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-20T16:10:39.856Z","status":"ssl_error","status_checked_at":"2026-01-20T16:10:39.493Z","response_time":117,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["ai","livekit","llm","ollama","openai","python","stt","tts"],"created_at":"2025-05-19T22:13:58.068Z","updated_at":"2026-01-20T16:26:40.561Z","avatar_url":"https://github.com/extrawest.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🎙️ Voice-to-Voice Communication Assistant\n\n[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)]()\n[![Maintainer](https://img.shields.io/static/v1?label=Yevhen%20Ruban\u0026message=Maintainer\u0026color=red)](mailto:yevhen.ruban@extrawest.com)\n[![Ask Me Anything !](https://img.shields.io/badge/Ask%20me-anything-1abc9c.svg)]()\n[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n![Version](https://img.shields.io/badge/version-1.0.0-blue)\n\nA scalable voice assistant implementation using LiveKit for real-time communication, with custom Speech-to-Text (STT) and Text-to-Speech (TTS) integrations using local APIs.\n\n\n\nhttps://github.com/user-attachments/assets/0e8ccc11-c21f-4d22-9904-eccede307123\n\n\n\n## 🚀 Features\n\n- **🗣️ Voice-to-Voice Communication**: Real-time voice interaction with an AI assistant\n- **🔌 Local API Integration**: Uses local APIs for STT, TTS, and LLM processing\n  - Custom STT using local Speeches AI API\n  - Custom TTS using local Kokoro AI API\n  - Integration with Ollama for local LLM processing\n- **🛠️ Additional Tools**:\n  - 🔍 Web search capability using Tavily API\n  - 🌤️ Weather information retrieval\n- **🔄 LiveKit Integration**: Leverages LiveKit's powerful real-time communication framework\n- **🎤 Voice Activity Detection**: Uses Silero VAD for accurate speech detection\n- **🔇 Noise Cancellation**: Integrated noise reduction for better audio quality\n\n## 📋 Prerequisites\n\n- Python 3.10+\n- LiveKit server (local or cloud)\n- Local STT API (Speeches AI)\n- Local TTS API (Kokoro AI)\n- Ollama running locally\n\n## 💻 Installation\n\n1. Clone this repository:\n   ```bash\n   git clone https://github.com/extrawest/voice_to_voice_communication_assistant.git\n   cd voice_to_voice_communication_assistant\n   ```\n\n2. Create and activate a virtual environment:\n   ```bash\n   python -m venv .venv\n   source .venv/bin/activate\n   ```\n\n3. Install dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n4. Set up environment variables by copying the example file:\n   ```bash\n   cp .env.example .env\n   ```\n\n5. Edit the `.env` file with your configuration:\n   ```\n   # LiveKit Configuration\n   LIVEKIT_URL=ws://localhost:7880\n   LIVEKIT_API_KEY=devkey\n   LIVEKIT_API_SECRET=secret\n\n   # STT Configuration\n   STT_API_URL=your_url\n\n   # LLM Configuration\n   LLM_API_URL=your_url\n\n   # TTS Configuration\n   TTS_API_URL=your_url\n   TTS_API_KEY=your-api-key\n\n   # Optional API Keys for Additional Features\n   WEATHER_API_KEY=your-weather-api-key\n   TAVILY_API_KEY=your-tavily-api-key\n   ```\n\n## 🚀 Running the Application\n\n### Backend Setup\n\n1. Run the voice assistant backend:\n   ```bash\n   python main.py dev\n   ```\n\n### Frontend Setup\n\n1. Clone the LiveKit voice assistant frontend repository:\n   ```bash\n   git clone https://github.com/livekit-examples/voice-assistant-frontend\n   cd voice-assistant-frontend\n   ```\n\n2. Install dependencies and start the frontend:\n   ```bash\n   npm install\n   npm run dev\n   ```\n\n3. Open your browser and navigate to http://localhost:3000\n\n4. Start interacting with your voice assistant!\n\n## 🏗️ Architecture\n\nThe application consists of several key components:\n\n![Architecture Diagram](https://mermaid.ink/img/pako:eNp1kk1PwzAMhv9KlBMgdT3QA4deEEJiQmicJg5VG9M6tHFVJ9UK7b-T9mOlMHGK_T7PK8dZHrRFyXnpWtQOXlCZo0bVQW3QgbKwQVNBZQ1Uh1rBGvUOKgRrLTkMVhsXYI_WoYEXVB0qgzXVIEONDmwNO3QWFG4DKKqtQRlgj3uEV-3I5RO8aUdlEBTUxkKHDRTGNh3UgWw-wVk0sEKDJhA8aEtVnmGnHdFCYbQJRJMHWKKhDgJZKFzQJRrXQxHI5gPMUPXaOWgCwSNqS1We4QlVQ7QQyOYDvGlDdgLBHVpHVZ7hGVVLtBDI5gO8GHQmEDygdVTlGc7QdEQLgWw-wBKNDgQP2jmq8gxrNB3RQiCbD_DJHwkEj9o5qvIMG-06ooVANv_DGxpLr3CC1lGVZ9hq1xItBLL5AO_aUJVA8KSdoyrP8KJdR7QQyOYDfNKvCQRP2lmq8gxb7TqihUA2H-ATDf2aQPBZO0tVnmGvXUe0EMjmA3zQrwkEz9pZqvIMB-06ooVANv_DK5qefk0geNHOUpVnOGrXES0EsvkA_-SvCQTP2lmq8gxH7TqihUA2H-CdXk0gWGjnqMozfNWuJVoIZPMBPtBQlUBwp52jKs_wTbuWaCGQzQf4i35NIHjVzlGVZzhp1xItBLL5AO_0awLBQjtLVZ7hpF1HtBDI5gMc6NcEgmftLFV5hm_atUQLgWw-wLEPgeBFO0dVnuGkXUu0EMjmA-z71wSChXaWqjzDSbuOaCGQzQc49K8JBM_aWaraf_8AYdAm0Q?type=png)\n\n- **LiveKit Integration**: Handles real-time audio streaming and room management\n- **Custom STT Class**: Processes audio input and converts it to text\n- **Custom TTS Class**: Converts text responses to speech\n- **Ollama LLM Integration**: Processes text input and generates responses\n- **Agent Implementation**: Manages the conversation flow and tools\n\nDeveloped by [extrawest](https://extrawest.com/). Software development company\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fextrawest%2Fvoice_to_voice_communication_assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fextrawest%2Fvoice_to_voice_communication_assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fextrawest%2Fvoice_to_voice_communication_assistant/lists"}