Features
Generate avatar videos from script, brief, deck, or document
Real-time Visual AI Agents with face-to-face conversation
V4 Expressive Avatars for emotionally intelligent interactions (Feb 2026)
Voice cloning and multilingual output (120+ languages)
Agentic Videos merging pre-recorded video with conversational AI (Apr 2026)
LiveKit plug-in for real-time visual agent experiences (Apr 2026)
Video Studio for polished, multilingual video creation
AI Avatars built from images or video
Real-time streaming animation via API
Video translation and localization
Custom training of agents on proprietary knowledge bases
Mobile app for on-the-go creation (not confirmed, but in old profile)
Enterprise-grade privacy, security, and compliance
Integrations with PowerPoint, Canva, Google Slides, Articulate, ElevenLabs
Real-time video generation with emotional intelligence (Phoenix-4)
Multimodal perception: face, tone, gaze, environment (Raven-1)
Low-latency conversational turn-taking (Sparrow-1)
Custom replica training from 2-minute video with custom voice model
Knowledge Base with RAG at 30ms
Memories, Objectives, and Guardrails for agent behavior
Persona Builder for custom agent personalities
Test mode for conversations (no cost or concurrency usage)
Events Console for real-time monitoring and debugging
Conversation transcripts with perception analysis
WebRTC API for real-time video streaming
No-code portal (PAL Maker) to create and deploy PALs
Enterprise white-labeling, SOC2/HIPAA compliance, SLAs
