Photorealistic avatars that speak your voice agent's audio in real time
Personalized AI songs in about a minute
Stage
Not given
Startup
Founded
Not given
2026
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 song for $19.99, 3 songs for $39.99, 8 songs for $69.00. One-time payment, no subscription. Your first song is free to preview for 45 seconds.
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
Free 45-second preview of first song
Edit lyrics with up to 25 revisions
Download songs as MP3
Shareable gift pages with custom messages
Full songs approximately 2 minutes 30 seconds long
30-day refund policy for unused songs
No subscription, one-time payment packs
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
Recipient's name sung in first line for personalized songs
Free preview before paying, unlike general music tools
Much faster and cheaper than hiring a human songwriter
Simple, story-driven form instead of open-ended prompts