Photorealistic avatars that speak your voice agent's audio in real time
AI-powered tool to edit text in finished images while matching the original font and background
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Paid
Freemium
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.
1 free edit for new accounts. One-time credit packs: Try $3.90 (8 edits, $0.49 per edit), Starter $14.90 (40 edits, $0.37 per edit), Pro $26.90 (100 edits, $0.27 per edit). No subscription.
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
Edit text while keeping original font, color and spacing
Automatic background restoration
Compare before and after with slider and highlight tool
Support for PNG, JPEG and WebP files up to 10 MB
Automatic credit refund on failed edits
Two editing modes: Fast (1K) and Pro (2K)
Translate text to Chinese, Japanese and Korean
No source file or original font needed
Commercial use allowed on owned or editable images
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
No subscription required – pay once for credits that never expire
See exactly what changed before downloading with slider and highlight verification
Restores background from original image when changes are contained