Realistic Avatars: $0.02 per minute, billed per second. Voice Agents: $0.06 per minute, billed per second. Open Source: Free (MIT License). Custom avatar: $199 per avatar (one time). Remove watermark: $19 per month. New accounts get $1 of free credits.
Key features
30-second seamless video generation in single continuous clip
Up to 50 multimodal reference inputs including images, video, audio and 3D blockouts
Native audio-video generation
Local editing to refine single details without re-rendering
1080p HD video quality
Commercial use license included
Scene-level control directing pacing and emotional beats
AI image generation
Multiple aspect ratio and duration options
Priority download speed and customer support in premium tiers
Real-time lip-sync with accurate mouth shapes from audio alone
Works with any TTS or voice provider (OpenAI, ElevenLabs, Azure, Fish Audio, Cartesia)
Avatar responds in less than 250 milliseconds
WebRTC delivery with video and audio in sync, no media servers required
LiveKit integration for drop-in avatar as participant
SDK with server and client libraries for quick integration
User interruption support to stop avatar mid-sentence
Sessions can run up to 3 hours each
Works with any language audio
No text or viseme data required
What makes it different
Native single-segment video output up to 30 seconds requires no stitching
Supports up to 50 combined multimodal inputs in one generation
Local editing allows refining single scene details without full re-render
ByteDance Seedance 2.5 model with native audio-video generation
Credits never expire and carry over indefinitely
Photorealistic avatars that require no 3D work or custom training
Ultra-low latency under 250 milliseconds
Affordable pricing from $0.02 per minute, billed per second with no minimum
Talking Avatar