Youragent has a voice.Now give it a face.

# Add Anam to an existing or new VideoSDK app

Inspect this repository before changing code: identify its framework/runtime, package manager, lockfile, agent entrypoint and private server configuration. If a VideoSDK integration exists, extend it in place. Otherwise, use the documented starter below to create the missing integration without overwriting unrelated files. Infer runtime/provider choices from the user's request and repository; ask only when a material choice cannot be inferred.

Before implementing, fetch https://docs.videosdk.live/ai_agents/plugins/avatar/anam-ai and the relevant partner setup references below. Use https://anam.ai/docs/llms.txt to discover additional Anam pages as needed. Cross-check installed SDK types/source when live docs disagree with the package version. Do not invent APIs or silently combine incompatible examples. If sources are unavailable or conflict, report what is unverified.

Set the Anam avatar model to "cara-4.1-express" in every configuration. Do not inherit a catalog default or fall back to another model.

The reference architecture is: The videosdk-plugins-anam plugin adds AnamAvatar to Pipeline through the avatar parameter, using either speech providers or a realtime model passed as llm. The agent's audio drives synchronized avatar audio and video published as a VideoSDK room participant.

Integration-specific setup:

- Follow https://docs.videosdk.live/ai_agents/plugins/avatar/anam-ai. Current versions use videosdk.agents.Pipeline for both modes; pass a realtime model as llm=model. Anam's older cookbook examples use legacy pipeline classes, so check the installed release before adapting them.
- Inspect the installed videosdk-agents and videosdk-plugins-anam versions and runtime constraints together. Current plugin releases require Python >=3.12,<3.14; check https://pypi.org/pypi/videosdk-plugins-anam/json for the exact required Agents version. For a legacy app, resolve compatibility without an unrequested framework migration; for a new app, verify current compatible stable releases.
- For a new project, follow https://docs.videosdk.live/ai_agents/voice-agent-quick-start. Include agent/session startup, VideoSDK authentication, room creation/room ID shared by agent and client, provider credentials, ANAM_API_KEY and ANAM_AVATAR_ID. Use web/room mode and a client that renders avatar video; console voice-only mode cannot verify it.
- Preserve the configured speech providers or native-audio model, turn detection and interruption behavior; attach AnamAvatar through the pipeline's avatar argument.

Requirements:

- Preserve existing providers, tools, system prompts and business logic within the selected documented integration mode. Do not replace the app's architecture or write persistent agent-rules files without a user request.
- Keep the Anam API key in private server-side configuration. Never expose or request it in client code or chat.
- Preserve compatible installed versions and the project's package manager. For a fresh project, resolve current compatible stable releases and record them in the lockfile; do not use remembered versions or force unrelated upgrades.
- Implement the missing imports, environment loading, backend/agent startup, session/room authentication and frontend video rendering required by the chosen starter. The fragments below assume configured providers and entrypoint variables; do not copy them as standalone programs.
- When extending an existing voice app, preserve its voice-only path when Anam is not configured and log a clear warning. Missing optional avatar config must not prevent the ordinary voice session from starting.
- Check types/build and relevant tests. When credentials are available, verify visible synchronized video, one audio output, working tools/interruptions and stop/disconnect cleanup. State explicitly which live checks could not run.
- Summarize changed files, placeholder-only environment variables, exact install/run commands, package versions and verification results. Never fabricate credentials or claim an unrun check passed.

Reference fragments — use only the matching runtime/mode:

## Python · Cascading

```python
# 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
from anam.types import PersonaConfig

avatar = AnamAvatar(
    api_key=os.environ["ANAM_API_KEY"],
    persona_config=PersonaConfig(
        avatar_id=os.environ["ANAM_AVATAR_ID"],
        avatar_model="cara-4.1-express",
        enable_audio_passthrough=True,
    ),
)

# Keep your existing speech providers and turn detection.
pipeline = Pipeline(
    stt=stt,
    llm=llm,
    tts=tts,
    vad=vad,
    turn_detector=turn_detector,
    avatar=avatar,
)
```

## Python · Realtime

```python
# 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
from anam.types import PersonaConfig

avatar = AnamAvatar(
    api_key=os.environ["ANAM_API_KEY"],
    persona_config=PersonaConfig(
        avatar_id=os.environ["ANAM_AVATAR_ID"],
        avatar_model="cara-4.1-express",
        enable_audio_passthrough=True,
    ),
)

# Keep your configured native audio model, e.g. Gemini Live.
pipeline = Pipeline(llm=model, avatar=avatar)
# The avatar streams synchronized audio and video into the room.
```

If live docs differ from these fragments, check the installed implementation and explain the version-specific correction before using it.