# table-read

- **Event:** [Cartesia x Anthropic Voice Agents Hackathon hosted by Notion](https://cerebralvalley.ai/e/cartesia-voice-agents-hackathon)
- **When:** Feb 7 at 9:00 AM – Feb 8 at 3:30 PM (PST)
- **Where:** Notion HQ, San Francisco, CA
- **Team:** [Tingyu Zhang](https://cerebralvalley.ai/u/robertzty), [Rick Yang](https://cerebralvalley.ai/u/BigBigRick), [Robert Zhang](https://cerebralvalley.ai/u/rzintbot)
- **GitHub:** https://github.com/yanxiyc/table-read
- **Demo video:** https://youtu.be/BFenIvWqP68?si=HBWVsyUXZlwl2g0S
- **Gallery:** https://cerebralvalley.ai/e/cartesia-voice-agents-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/cartesia-voice-agents-hackathon/hackathon/gallery/4

Table Read is an AI-powered script rehearsal app where actors practice scenes with an AI scene partner and receive real-time directing feedback.

A human actor joins a LiveKit voice room and rehearses a scripted scene beat-by-beat with an AI character agent (powered by Cartesia Sonic-3 TTS and Anthropic Claude). A separate AI Director agent listens to each delivery in real time, evaluates whether the actor is truly acting or merely reading, and provides scoring, engagement analysis, and actionable notes. Scenes are managed via a Notion database and a Next.js frontend, and the final rehearsed script can be locked as a versioned artifact.

---

Markdown version of https://cerebralvalley.ai/e/cartesia-voice-agents-hackathon/hackathon/gallery/4. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt