{"id":13910482,"url":"https://github.com/haseeb-heaven/gemini-vision-pro","last_synced_at":"2025-04-10T13:30:29.508Z","repository":{"id":212998221,"uuid":"732513959","full_name":"haseeb-heaven/gemini-vision-pro","owner":"haseeb-heaven","description":"Google Gemini Vision Web application with Speech and Text","archived":false,"fork":false,"pushed_at":"2024-01-23T04:48:43.000Z","size":65,"stargazers_count":45,"open_issues_count":0,"forks_count":16,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-10T08:59:50.780Z","etag":null,"topics":["bard","chatgpt","cv2-library","gemini","gemini-ai","gemini-api","google","google-ai","google-bard","google-cloud","google-gemini","google-studio","gpt","image-processing","opencv","python","python-cv2","python-image-processing"],"latest_commit_sha":null,"homepage":"https://gemini-studio.streamlit.app","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/haseeb-heaven.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}},"created_at":"2023-12-16T23:24:46.000Z","updated_at":"2024-10-22T00:29:20.000Z","dependencies_parsed_at":"2023-12-17T21:27:54.280Z","dependency_job_id":"4030b9c9-fdf4-452d-b8c7-b5020aca687c","html_url":"https://github.com/haseeb-heaven/gemini-vision-pro","commit_stats":{"total_commits":20,"total_committers":2,"mean_commits":10.0,"dds":"0.050000000000000044","last_synced_commit":"c2b9159097e129c0d94f70476c19c0202be969f7"},"previous_names":["haseeb-heaven/gemini-vision-pro"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haseeb-heaven%2Fgemini-vision-pro","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haseeb-heaven%2Fgemini-vision-pro/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haseeb-heaven%2Fgemini-vision-pro/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haseeb-heaven%2Fgemini-vision-pro/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/haseeb-heaven","download_url":"https://codeload.github.com/haseeb-heaven/gemini-vision-pro/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248225705,"owners_count":21068078,"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":["bard","chatgpt","cv2-library","gemini","gemini-ai","gemini-api","google","google-ai","google-bard","google-cloud","google-gemini","google-studio","gpt","image-processing","opencv","python","python-cv2","python-image-processing"],"created_at":"2024-08-07T00:01:28.632Z","updated_at":"2025-04-10T13:30:29.471Z","avatar_url":"https://github.com/haseeb-heaven.png","language":"Python","funding_links":["https://www.buymeacoffee.com/haseebheaven","https://img.buymeacoffee.com/button-api/?text=Buy"],"categories":["Python"],"sub_categories":[],"readme":"\u003cimg src=\"https://www.gettingstarted.ai/content/images/2023/12/GS-Beginner-Guide-Using-Google-Gemini-Pro-Vision-Google-AI-Studio.png\" alt=\"Gemini Vision Pro Logo\" width=\"640\" height=\"480\"\u003e\n\n\n\u003ca href=\"https://www.buymeacoffee.com/haseebheaven\"\u003e\u003cimg src=\"https://img.buymeacoffee.com/button-api/?text=Buy me a coffee\u0026emoji=\u0026slug=haseebheaven\u0026button_colour=40DCA5\u0026font_colour=ffffff\u0026font_family=Cookie\u0026outline_colour=000000\u0026coffee_colour=FFDD00\" /\u003e\u003c/a\u003e\n\n\n🚀 **_Description:_** 🚀 This is the amazing Google Gemini Vision Pro 📸, a powerful tool that scans images, generates descriptions using Gemini AI Pro Vision API, and provides speech feedback 🗣️. It also captures images using the webcam 🖥️.\n\n## 🌟 **Introduction** 🌟\n\nGoogle Gemini Vision Pro is a versatile application that combines image processing 🖼️, speech recognition 🎤, and text-to-speech capabilities 📢. With this application, you can capture images using your webcam 📷, convert spoken words to text 📝, generate image descriptions 📚, and even have the descriptions spoken back to you 📣.\n\n## **Installation Guide**\n\n### **_Step 1: Clone the repository_**\n\n```bash\ngit clone https://github.com/haseeb-heaven/Gemini-Vision-Pro\ncd Gemini-Vision-Pro\n```\n\n## **_Step 2: Install the dependencies_**\n\n```bash\npip install -r requirements.txt\n```\n\n## **_Step 3: Run the application_**\n\n```bash\nstreamlit run script.py\n```\n\n## **_Step 4: Obtain the Google Palm API key and Setup the application_**\n\n1. **_Obtain the Google Palm API key._**\n2. Visit the following URL: [Google AI Studio](https://makersuite.google.com/app/apikey)\n3. Click on the **_Create API Key_** button.\n4. The generated key is your API key. Please make sure to **_copy it and paste it in the application settings_**.\n5. The API key is crucial for the functioning, **_Please ensure to keep it safe and do not share it with anyone_**.\n\n### Gemini AI settings:\n\u003cimg src=\"https://i.ibb.co/Jpj1pc6/gemini-ai-settings.png\" alt=\"Gemini Settings\" width=\"340\" height=\"240\"\u003e\n\n## **AI Sections**\n\nThe core AI sections of this project include:\n- 📷 **Webcam detection** using WebRTC, OpenCV, and PIL\n- 🗣️ **Speech-to-text conversion** using Google Cloud Speech-to-Text API\n- 🎙️ **Text-to-speech conversion** using Google Cloud Text-to-Speech API\n- 📸 **Image processing** using Gemini AI Pro Vision API\n\n## **Features**\n\n- 📷 Webcam detection with real-time image capture\n- 🗣️ Speech-to-text conversion for spoken words\n- 🎙️ Text-to-speech for generating spoken descriptions\n- 📸 Image processing using AI to provide detailed descriptions\n- 📝 Logging using Python's logging module\n- ⚙️ Error handling with Python's exception handling\n\n## **WebUI - Application Showcase**\n\n### YouTube demo:\n[![Gemini Vision demo](https://i.ibb.co/0c0kzXY/gemini-youtube-img.png)](https://www.youtube.com/shorts/DkwDIDc0ufI)\n\n\n### Webcam with live feed:\n\n\u003cimg src=\"https://i.ibb.co/wMLp5FX/gemini-ai-webcam.png\" alt=\"Webcam with live feed\" width=\"720\" height=\"1280\"\u003e\n\n### Gemini Ai Vision demo with object as Cap:\n\n\u003cimg src=\"https://i.ibb.co/1zk68bV/gemini-ai-demo2.png\" alt=\"Gemini Ai Vision Cap\" width=\"720\" height=\"1280\"\u003e\n\n### Gemini Ai Vision demo with Hand:\n\n\u003cimg src=\"https://i.ibb.co/BnzB1B9/gemini-ai-demo3.png\" alt=\"Gemini Ai Vision Hand\" width=\"720\" height=\"1280\"\u003e\n\n### Gemini Ai Vision demo with Gesture:\n\n\u003cimg src=\"https://i.ibb.co/kJ9LHrH/gemini-ai-demo4.png\" alt=\"Gemini Ai Vision Gesture\" width=\"720\" height=\"1280\"\u003e\n\n\n## **Packages Used**\n\nThis project relies on various Python packages, including:\n- Streamlit - A web app framework used to build the application\n- Streamlit Webrtc - Used for capturing images from the webcam\n- OpenCV - Utilized for webcam image capture\n- PIL (Pillow) - Used for image processing and conversion\n- gTTS (Google Text-to-Speech) - Converts text to speech\n- SpeechRecognition - Converts speech to text\n- google.cloud.speech - Part of Google Cloud services for speech-to-text conversion\n\n## 📚 **Links and References**\nFollow these links for **Google Gemini Vision Pro** related content:\n- [**Google AI Studio**](https://makersuite.google.com/app/apikey)\n- [**Google Gemini Vision Pro**](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini)\n- [**Google Gemini Deepmind**](https://deepmind.google/technologies/gemini/)\n\n## **Versioning**\n\n- **Version**: 1.0 : Initial Release\n\n## **Contributing**\n\nWe welcome contributions! Please follow our [**Contribution Guidelines**](CONTRIBUTING.md) to get started.\n\n## **License**\n\nThis project is licensed under the **MIT License** - see the [**LICENSE**](LICENSE) file for details.\n\n## **Author**\n\n- **_HeavenHM_**\n- **_Date:_** 17-12-2023\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhaseeb-heaven%2Fgemini-vision-pro","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhaseeb-heaven%2Fgemini-vision-pro","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhaseeb-heaven%2Fgemini-vision-pro/lists"}