Submission by Rolla

1. What did you build? I built AetherVoice, a hardware-anchored AI agentic bridge that combines biometric security with personalized voice AI. It allows users to interact with their digital twin or autonomous agent using only their voice, secured by a hardware-level root of trust. By leveraging the AetherUX protocol, we’ve created a system where an AI agent only "wakes up" and speaks when the user's hardware identity (Secure Enclave) is biometrically verified. 2. What problem does it solve? Current AI voice agents face two massive hurdles: Identity Fraud (Deepfakes) and Context Fragmentation. Security: Most voice bots have no way to verify the speaker is actually the authorized owner. AetherVoice solves this by requiring a hardware-anchored secp256r1 Passkey handshake before the agent vocalizes or accesses private data. Onboarding Friction: We eliminate the need for seed phrases and manual logins. Your voice and your biometric hardware are your identity. Memory Persistence: Traditional agents forget context. We use a high-performance vector memory to ensure agents have long-term, secure recall of past interactions. 3. How does it use ElevenLabs and turbopuffer? ElevenLabs: Powers the agent's vocal identity. We use ElevenLabs' high-fidelity voice design to create a persistent, recognizable "Vocal Fingerprint" for the agent. This voice is biometrically locked—it will only speak authorized responses once the AetherUX handshake is successful, preventing unauthorized audio generation. turbopuffer: Serves as the agent's Sovereign Memory. We use turbopuffer’s serverless vector search to store and retrieve millions of historical conversation fragments and user preferences. Because turbopuffer is 10-100x more cost-effective than traditional vector DBs, we can provide each user with a dedicated, massive "Memory Namespace" that allows for near-instant, semantic recall (RAG) during live voice conversations, all while maintaining sub-10ms response times for a natural "Invisible" UI experience.