Sapphire's Captioning Service

Created by team SapphireVIP on July 08, 2026
Video Captioning

Sapphire Video Captioning Agent is a Track 2 video captioning submission for the AMD Developer Hackathon ACT II. The container reads tasks from /input/tasks.json, downloads each video, prepares it with ffmpeg, and sends it through a Cloudflare Worker proxy to a vision-language model via OpenRouter. For every requested clip, it returns valid JSON to /output/results.json with captions for the required styles: formal, sarcastic, humorous_tech, and humorous_non_tech. The project focuses on faithful visual descriptions, concise language, style matching, retries, fallback captions, and the exact input/output contract required by the challenge.

Category tags: