@krishna652dev61109

This project is an AI-powered video captioning system designed to understand both the visual and audio content of a video and generate meaningful captions in multiple styles. The system first extracts key frames and audio from the uploaded video. OpenAI Whisper is used to convert speech into text, while a multimodal vision-language model analyses the extracted frames to identify people, actions, objects, settings, and scene changes. The audio transcript and visual description are then combined to understand the complete context of the video. Based on this combined information, the system generates captions in formal, sarcastic, humorous-tech, and humorous-non-tech tones. The project demonstrates practical use of computer vision, speech recognition, multimodal AI, prompt engineering, and structured JSON output generation.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.