Documentation Index
Fetch the complete documentation index at: https://docs.agenthuman.com/llms.txt
Use this file to discover all available pages before exploring further.
Overview
AgentHumanVideoService is a Pipecat AIService that slots into your pipeline right after your TTS service. It receives TTS audio frames, sends them to the AgentHuman avatar via a LiveKit data stream, and injects the avatar’s video and audio frames back into the pipeline for your output transport to publish.
Perfect for:
- Voice AI applications with a visual presenter
- Conversational agents with animated avatars
- Real-time speech-driven video generation
- Interactive AI assistants
How It Works
AgentHumanVideoService handles everything internally:
- Creates an AgentHuman session via the REST API on startup
- Connects to the returned LiveKit room
- Resamples TTS audio to 16 kHz mono and streams it to the avatar
- Forwards the avatar’s video and audio frames downstream to your transport
Installation
pipecat.services.agenthuman: import AgentHumanVideoService from pipecat.services.agenthuman.video and NewSessionRequest from pipecat.services.agenthuman.api.
The
agenthuman extra installs the LiveKit SDK (livekit) required for the avatar data stream. The Examples use additional Pipecat extras (daily, deepgram, elevenlabs, google, and python-dotenv) — install those alongside agenthuman when you run the full bot.Environment Variables
| Variable | Description |
|---|---|
AGENTHUMAN_API_KEY | Your AgentHuman API key |
Next Steps
Quick Start
Add AgentHumanVideoService to your pipeline in minutes
Configuration
All parameters and transport requirements
Examples
Complete working bot examples
API Reference
Underlying session API