Dream Manifest (Personal Project)

March 07, 2025

2025   ·   gemini   videos   demo     ·   personal-project  

This API extracts speech from video, transcribes it to insight text, and generates images from that text using Google’s Gemini AI — a complete pipeline from video to visuals. Check here for details.



Enjoy Reading This Post?

Here are some more posts you might like to read next:

  • Multi-AI Agent for Discord (Personal Project)
  • Llama Paper Summary (Personal Project)
  • MSTA3D - Multi-scale Twin-attention for 3D Instance Segmentation
  • Mobile Robot (Personal Project)
  • 3DoF Arm Robot (Personal Project)