Youragent has a voice.Now give it a face.

# Add Anam to an existing or new Pipecat app

Inspect this repository before changing code: identify its framework/runtime, package manager, lockfile, agent entrypoint and private server configuration. If a Pipecat 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://github.com/anam-org/pipecat-anam 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 pipecat-anam service turns the pipeline's text-to-speech output into synchronized avatar video before transport output.

Integration-specific setup:

- Use https://github.com/anam-org/pipecat-anam and its full example at https://github.com/anam-org/pipecat-anam/blob/main/examples/video-avatar-anam-video-service.py. Check examples against the installed release: the repository's main branch may contain prerelease APIs.
- A new project needs a supported video-capable transport, its client, provider credentials, ANAM_API_KEY, ANAM_AVATAR_ID, and the documented pipeline task/runner. Install compatible pipecat-anam and transport/provider dependencies; keep the existing transport when supported.
- Enable video_out_enabled=True and video_out_is_live=True in the selected transport's actual params before startup, retain audio output, and match frame dimensions/client rendering. See https://docs.pipecat.ai/api-reference/server/services/transport/transport-params. If the existing transport cannot carry video, explain the needed transport change before implementing it.
- Insert AnamVideoService after TTS and before transport.output(), preserving context aggregation and interruptions. Use Cara-4.1 Express with audio passthrough; verify the chosen avatar/model and shut down the pipeline/transport cleanly.

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

```python
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-4.1-express",
        enable_audio_passthrough=True,
    ),
)

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

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