{"id":29005445,"url":"https://github.com/absarraashid3/visionwhiz","last_synced_at":"2025-06-25T11:33:17.252Z","repository":{"id":301031066,"uuid":"1007949638","full_name":"AbsarRaashid3/VisionWhiz","owner":"AbsarRaashid3","description":"VisionWhiz is a futuristic AI-powered web application that allows users to ask questions about any image using voice or text—and receive intelligent answers, both spoken and displayed. By integrating powerful models from OpenAI, Salesforce, and Google, VisionWhiz delivers real-time, context-aware visual interaction through a sleek Gradio interface.","archived":false,"fork":false,"pushed_at":"2025-06-24T19:41:41.000Z","size":6,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-24T20:41:36.208Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/AbsarRaashid3.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,"zenodo":null}},"created_at":"2025-06-24T19:34:53.000Z","updated_at":"2025-06-24T19:41:44.000Z","dependencies_parsed_at":"2025-06-24T20:41:38.292Z","dependency_job_id":"48cd50e1-9452-417b-aa6d-0694166db0c6","html_url":"https://github.com/AbsarRaashid3/VisionWhiz","commit_stats":null,"previous_names":["absarraashid3/visionwhiz"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AbsarRaashid3/VisionWhiz","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AbsarRaashid3%2FVisionWhiz","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AbsarRaashid3%2FVisionWhiz/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AbsarRaashid3%2FVisionWhiz/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AbsarRaashid3%2FVisionWhiz/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AbsarRaashid3","download_url":"https://codeload.github.com/AbsarRaashid3/VisionWhiz/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AbsarRaashid3%2FVisionWhiz/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261863509,"owners_count":23221564,"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":[],"created_at":"2025-06-25T11:31:17.557Z","updated_at":"2025-06-25T11:33:17.231Z","avatar_url":"https://github.com/AbsarRaashid3.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# VisionWhiz: Talk to Your Image AI\nVisionWhiz is a futuristic AI-powered web application that allows users to ask questions about any image using voice or text—and receive intelligent answers, both spoken and displayed. By integrating powerful models from OpenAI, Salesforce, and Google, VisionWhiz delivers real-time, context-aware visual interaction through a sleek Gradio interface.\n\n#  Project Overview\nThe goal of VisionWhiz is to:\n\nEnable natural, multimodal interaction with images through voice and text.\n\nSeamlessly integrate speech recognition, visual question answering, and text-to-speech features.\n\nImprove accessibility and elevate the human-computer interaction experience.\n\n#  Features\nVoice \u0026 Text Input\nSpeech-to-Text: Speak your question naturally (powered by openai/whisper-small).\n\nText Input: Optionally, type your question into the input box.\n\n#  Visual Intelligence\nImage Upload: Upload any image for interactive questioning.\n\nVisual Question Answering: Get accurate, context-aware answers using Salesforce/blip-vqa-base.\n\n#  Smart Audio Output\nText-to-Speech: Listen to the answer read out loud with Google’s gTTS.\n\n# Interactive Interface\nGradio Frontend: Built with Gradio and custom CSS for a clean, modern UI.\n\nSmooth, real-time interaction across all components.\n\n# Tech Stack\nComponent\tModel/Library\nSpeech-to-Text\topenai/whisper-small (HuggingFace)\nImage QA\tSalesforce/blip-vqa-base\nText-to-Speech\tgTTS (Google Text-to-Speech)\nUI Framework\tGradio\nAudio/Image I/O\ttorchaudio, soundfile, PIL\n\n# Project Structure\nbash\nCopy\nEdit\nVisionWhiz/\n├── app.py               # Main app logic and Gradio interface\n└── README.md            # Project documentation\n#  Use Cases\n Ask what’s happening in any image using natural language.\n\n Create accessible educational tools with audio support.\n\n Aid users with visual impairments or reading difficulties.\n\n Prototype intelligent assistants for vision-language tasks.\n# ARCHITECTURE DIAGRAM\n![1_FXFCM5IrtGG3xyTr97-ONg](https://github.com/user-attachments/assets/df481120-acf2-41e5-83b9-f10ce6300292)\n\n# Performance Snapshot\n\u003cimg width=\"1309\" alt=\"Screenshot 2025-06-25 at 12 39 13 AM\" src=\"https://github.com/user-attachments/assets/fa426525-683d-47fc-b454-b3540f317a13\" /\u003e\n\u003cimg width=\"1330\" alt=\"Screenshot 2025-06-25 at 12 39 27 AM\" src=\"https://github.com/user-attachments/assets/49d204f4-b9b9-43a4-b037-5381ca3e4e3c\" /\u003e\n\n# Developed by\nAbsar Raashid\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabsarraashid3%2Fvisionwhiz","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fabsarraashid3%2Fvisionwhiz","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabsarraashid3%2Fvisionwhiz/lists"}