Photorealistic avatars that speak your voice agent's audio in real time
AI video generator with text, image, reference or document input, up to 30 seconds with native audio at 1080P
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
AU
Pricing model
Paid
Paid
Pricing
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.
Not given
Key features
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
Image to video from first frame, last frame, or both
Reference to video with up to 10 images, 5 video clips and 5 audio tracks
Document or web page to video conversion
Video editing and rewriting without regeneration
Output up to 30 seconds in a single pass at 30 fps
Three resolution tiers: 480P, 720P, 1080P
Audio including speech, effects and music generated natively
Failed generations automatically return credits
Commercial use rights included on all paid plans
What makes it different
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
Only interface showing Alibaba's API task receipts with every generated video for full transparency
Document and web page to video, unique to Wan 3.0 and not offered by competing models
All input modes and full 1080P resolution included on lowest paid plan at $12.90 per month
Twice the single-pass length and three times the prompt characters versus nearest competitor
Independent third-party interface with transparent pricing and all specs linked to Alibaba's official documentation
Talking Avatar
wan-3.run