Your
agent has a voice.Now give it a face.
Add a real-time, photorealistic avatar to your VideoSDK voice agent with Anam's native plugin. Keep your STT, LLM, and TTS, or use a native audio model like Gemini Live, and stream the avatar directly into your VideoSDK room.
See it for yourself
Start a voice conversation, then flip the switch and watch how the avatar stays in sync without restarting the session or rebuilding your VideoSDK agent.
Voice only Voice + Anam Reveal the face
videosdk-agent-demo
Ready
Talk to the agent firstStart an audio-only conversation with your microphone.
videosdk-agent-demo · voice agent
KEEP EXPLORING
Build more with Anam + VideoSDK
01
VideoSDK agentSpeech pipeline or native audio
02
AnamLip sync · expression
03
VideoSDK roomAudio + video
VIDEOSDK AI AGENTS · PYTHON · CASCADING
From voice agent to video agent in a few lines.
Python · Cascading integration reference. Use Coding Agents to adapt these snippets to your app or create a project.
# Current API: use compatible videosdk-agents / videosdk-plugins-anam releases.
# Install with your package manager: uv add "videosdk-plugins-anam"
import os
from videosdk.agents import Pipeline
from videosdk.plugins.anam import AnamAvatar
avatar = AnamAvatar(
api_key=os.environ["ANAM_API_KEY"],
avatar_id=os.environ["ANAM_AVATAR_ID"],
)
# Keep your existing speech providers and turn detection.
pipeline = Pipeline(
stt=stt,
llm=llm,
tts=tts,
vad=vad,
turn_detector=turn_detector,
avatar=avatar,
)
Add a face to your VideoSDK agent.
Keep your current speech, language model, and voice stack. Add a synchronized avatar in a few lines.
