# Emilia

- **Event:** [GPT-6 Astra Hackathon NYC](https://cerebralvalley.ai/e/openai-gpt-6-astra-nyc)
- **When:** Thu, Sep 10 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Team:** [Boris Berenberg](https://cerebralvalley.ai/u/borisberenberg)
- **GitHub:** https://github.com/AbregaInc/Emilia-Mac/blob/main/docs/judges.md
- **Demo video:** https://github.com/AbregaInc/Emilia-Mac/blob/main/README.md
- **Gallery:** https://cerebralvalley.ai/e/openai-gpt-6-astra-nyc/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/openai-gpt-6-astra-nyc/hackathon/gallery/2

Emilia is an ongoing autoresearch project aiming to build a state-of-the-art detector for AI-generated audio. For the past few weeks, Codex and OpenAI’s latest models have helped direct experiments, evaluate results, and iterate on the detector.

For this hackathon, I built and shipped a native Mac app that brings the current Emilia detector into live conversations. It listens through the microphone or system audio and displays a click-through amber indicator when it detects synthetic-voice evidence. OpenAI Whisper or Realtime transcribes the conversation, and GPT-6 Astra combines the transcript with recent voice evidence to identify scam warning signs. Suspicious context triggers a red border and a warning grounded in the caller’s words.

The distinction matters: an automated appointment reminder can produce amber without red, while a synthetic voice claiming to be your daughter can prompt a warning to verify the caller.

The app, source code, and signed, notarized download are public. Emilia’s research predates the hackathon; the native app and live integrations were built during the event. Because the research uses rights-restricted data, we are not distributing the Emilia checkpoint. The public download instead includes a clearly labeled AASIST-L baseline; the demo uses actual Emilia v8.

---

Markdown version of https://cerebralvalley.ai/e/openai-gpt-6-astra-nyc/hackathon/gallery/2. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt