Photorealistic avatars that speak your voice agent's audio in real time
On-brand images and PDFs on autopilot
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
GB
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.
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
HTML to PDF conversion
HTML to image conversion
AI template generator from text
Image to template conversion
Brand kits for logo, colors, and fonts
Smart resize for multiple dimensions
Spreadsheet batch processing
ChatGPT and Claude integration via MCP
REST API for custom integrations
Zapier, Make, and n8n integrations
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
Works with your existing AI tools like ChatGPT and Claude through MCP connectors
Editable design layers instead of generated images, ensuring brand consistency
Free plan with 50 monthly credits, no card required
Same tools across all plans: templates, brand kits, AI builds
Talking Avatar
thirds.ai