Youragent has a voice.Now give it a face.

Add an expressive Anam avatar to the voice pipeline you already orchestrate with Pipecat. Your model and voice remain yours; Anam gives the conversation a face.

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 Pipecat agent.

Voice only Voice + Anam Reveal the face

Talk to the agent firstStart an audio-only conversation with your microphone.

pipecat-agent-demo · voice agent

KEEP EXPLORING

Build more with Anam + Pipecat

Docs Cookbook Blog

Your pipelineSTT · LLM · TTS

AnamLip sync · expression

Pipecat transportAudio + video

PIPECAT PIPELINES · PYTHON

From voice agent to video agent in a few lines.

Python integration reference. Use Coding Agents to adapt these snippets to your app or create a project.

Get API Key Read Integration Guide

import os
from anam import PersonaConfig
from pipecat.pipeline.pipeline import Pipeline
from pipecat_anam import AnamVideoService


# In your existing video-capable transport's params, set:
# video_out_enabled=True, video_out_is_live=True.
# Preserve audio output and configure matching video dimensions/client rendering.
avatar = AnamVideoService(
    api_key=os.environ["ANAM_API_KEY"],
    persona_config=PersonaConfig(
        avatar_id=os.environ["ANAM_AVATAR_ID"],
        avatar_model="cara-4",
        enable_audio_passthrough=True,
    ),
)


pipeline = Pipeline([
    transport.input(), stt, context_aggregator.user(), llm, tts,
    avatar,
    transport.output(),
    context_aggregator.assistant(),
])

Add a face to your Pipecat agent.

Keep your current speech, language model, and voice stack. Add a synchronized avatar in a few lines.

Start building Read the guide