{"id":18428631,"url":"https://github.com/adarshgurazada/voice-assistant-using-gemini","last_synced_at":"2026-04-28T18:31:14.402Z","repository":{"id":245983146,"uuid":"819745766","full_name":"Adarshgurazada/Voice-Assistant-Using-GEMINI","owner":"Adarshgurazada","description":"Gemini Chatbot","archived":false,"fork":false,"pushed_at":"2024-10-24T05:20:43.000Z","size":10,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-13T22:40:55.647Z","etag":null,"topics":["azure","azurecognitiveservice","gemini-api","porcupine","wakeword"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Adarshgurazada.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":"2024-06-25T06:02:36.000Z","updated_at":"2024-10-24T05:21:53.000Z","dependencies_parsed_at":"2024-06-25T07:59:15.984Z","dependency_job_id":"0ba7a398-4985-4531-86eb-ea1e5377cbc3","html_url":"https://github.com/Adarshgurazada/Voice-Assistant-Using-GEMINI","commit_stats":null,"previous_names":["adarshgurazada/voice-assistant-using-gemini-"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Adarshgurazada/Voice-Assistant-Using-GEMINI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adarshgurazada%2FVoice-Assistant-Using-GEMINI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adarshgurazada%2FVoice-Assistant-Using-GEMINI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adarshgurazada%2FVoice-Assistant-Using-GEMINI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adarshgurazada%2FVoice-Assistant-Using-GEMINI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Adarshgurazada","download_url":"https://codeload.github.com/Adarshgurazada/Voice-Assistant-Using-GEMINI/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adarshgurazada%2FVoice-Assistant-Using-GEMINI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32394215,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-28T14:34:11.604Z","status":"ssl_error","status_checked_at":"2026-04-28T14:32:37.009Z","response_time":56,"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":["azure","azurecognitiveservice","gemini-api","porcupine","wakeword"],"created_at":"2024-11-06T05:14:12.960Z","updated_at":"2026-04-28T18:31:14.387Z","avatar_url":"https://github.com/Adarshgurazada.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Voice Assistant Using GEMINI Pro LLM\n\n## Overview\n\nThis project showcases a voice assistant powered by the GEMINI Pro LLM, Azure Cognitive Services, and Porcupine wake word detection. The assistant listens for a specific wake word (\"Jarvis\") and responds to user queries with accurate and contextually appropriate answers. This system is designed for deployment on a rover bot used to scout around industrial areas and perform tasks with precision.\n\n## Features\n\n- **Wake Word Detection**: Utilizes Porcupine for detecting the wake word \"Jarvis\".\n- **Speech Recognition**: Converts spoken language into text using Azure Cognitive Services.\n- **Text Generation**: Generates responses using Google's GEMINI Pro LLM.\n- **Speech Synthesis**: Converts text responses back to speech using Azure Cognitive Services.\n- **Safety Filters**: Includes safety settings to block harmful content categories.\n\n## Setup\n\n### Prerequisites\n\n- Python 3.7 or higher\n- [Porcupine](https://picovoice.ai/platform/porcupine/) access key\n- Azure Cognitive Services subscription key\n- Google GEMINI Pro API key\n\n### Installation\n\n1. Clone the repository:\n\n    ```bash\n    git clone https://github.com/Adarshgurazada/Voice-Assistant-Using-GEMINI.git\n    cd Voice-Assistant-Using-GEMINI\n    ```\n\n2. Install the required Python packages:\n\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n3. Create a `.env` file in the root directory and add your API keys:\n\n    ```env\n    PORCUPINE=your_porcupine_key\n    AZURE=your_azure_key\n    GOOGLE_API=your_google_api_key\n    ```\n\n## Usage\n\n1. Run the main script:\n\n    ```bash\n    python main.py\n    ```\n\n2. The assistant will listen for the wake word \"Jarvis\". Once detected, it will prompt you to ask a question.\n\n3. Speak your query, and the assistant will process it, generate a response, and speak it back to you.\n\n## Code Explanation\n\n### Importing Libraries\n\n- **pyaudio**: For audio input and output.\n- **pvporcupine**: For wake word detection.\n- **azure.cognitiveservices.speech**: For speech recognition and synthesis.\n- **google.generativeai**: For text generation using GEMINI Pro LLM.\n- **dotenv**: For loading environment variables.\n\n### Initializing Services\n\n- **Porcupine**: Configured to detect the wake word \"Jarvis\".\n- **Azure Cognitive Services**: Configured for both speech recognition and synthesis.\n- **GEMINI Pro LLM**: Configured with generation and safety settings.\n\n### Main Loop\n\n- Continuously listens for the wake word using Porcupine.\n- Upon detecting the wake word, prompts the user for a query.\n- Converts the user's spoken query to text.\n- Sends the text to GEMINI Pro for a response.\n- Converts the generated response back to speech and plays it.\n\n## Contributing\n\n1. Fork the repository.\n2. Create a new branch (`git checkout -b feature-branch`).\n3. Make your changes.\n4. Commit your changes (`git commit -m 'Add new feature'`).\n5. Push to the branch (`git push origin feature-branch`).\n6. Open a pull request.\n\n\n## Contact\n\nFor any inquiries or feedback, please reach out to [adarsh.gurazada@gmail.com].\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadarshgurazada%2Fvoice-assistant-using-gemini","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadarshgurazada%2Fvoice-assistant-using-gemini","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadarshgurazada%2Fvoice-assistant-using-gemini/lists"}