← Latest products

Multimodal perception system for real-time conversation

Experience Raven-1, Tavus's multimodal perception model that understands not just what you say, but how you say it. See real-time tone, expression, and intent analysis. I work on real-time voice/video AI at Tavus and for the past few years, I’ve mostly focused on how machines respond in a conversation.

Visit raven.tavuslabs.orgexternal site

Reactions (1)

Similar products

by description similarity

  1. Sparrow-1

    tavus.io

    Audio-native model for human-level turn-taking without ASR

    Hacker News123 pts

  2. Sparrow-2

    sparrow2.tavuslabs.org

    Noise cancellation isn't designed for conversational AI

    Hacker News11 pts

  3. Real-time avatars that change emotions as you talk

    anam.ai

    Build real-time interactive AI avatars with Anam's API. Low-latency conversational video AI for customer service, training, and sales.

    Hacker News12 pts

  4. Real-time AI (audio/video in

    github.com

    voice out) on an M3 Pro with Gemma E2B

    Hacker News298 pts

  5. MARS5

    github.com

    open-source, insanely prosodic TTS model

    Hacker News24 pts