Forensics Drawer
Forensics Drawer is a voice-guided forensic sketch prototype that helps capture a witness description, structure it into a suspect schema, and generate sketch iterations from the collected details.
Core trick
Realtime voice interview extracts witness details into a structured suspect schema, which conditions gpt-image sketch iterations.
Description
Forensics Drawer is a voice-guided forensic sketch prototype that helps capture a witness description, structure it into a suspect schema, and generate sketch iterations from the collected details. It uses OpenAI Realtime voice models for the interview flow, with Whisper transcription configured via whisper-1. It uses GPT Image models, currently selectable as gpt-image-1, gpt-image-1.5, or gpt-image-1-mini, to generate the suspect sketch outputs.
https://github.com/tanaypai/openai-voice-hack