Anam Avatar Plugin for Vision Agents
Add real-time interactive avatar video to your AI agents using Anam's avatar API.
Features
- Real-time avatar video and audio synchronized with TTS output
- Audio passthrough mode for high-quality voice reproduction
- Automatic interruption when the user starts speaking
- Works with any TTS provider (ElevenLabs, Cartesia, etc.) or Realtime LLMs
- Configurable video resolution (default 1920x1080)
Installation
uv add "vision-agents[anam]"
# or directly
uv add vision-agents-plugins-anam
Quick Start
import asyncio
from uuid import uuid4
from dotenv import load_dotenv
from vision_agents.core import User, Agent
from vision_agents.plugins import anam, deepgram, elevenlabs, getstream, gemini
load_dotenv()
async def start_avatar_agent():
agent = Agent(
edge=getstream.Edge(),
agent_user=User(name="AI Assistant with Avatar", id="agent"),
instructions="You're a friendly AI assistant.",
llm=gemini.LLM(),
tts=elevenlabs.TTS(),
stt=deepgram.STT(),
avatar=anam.Avatar(),
)
call = await agent.create_call("default", str(uuid4()))
async with agent.join(call):
await agent.simple_response("Say hello.")
await agent.finish()
if __name__ == "__main__":
asyncio.run(start_avatar_agent())
Configuration
Environment Variables
ANAM_API_KEY=your_anam_api_key
ANAM_AVATAR_ID=your_anam_avatar_id
Avatar Options
anam.Avatar(
avatar_id=None, # Anam avatar ID (or set ANAM_AVATAR_ID env var)
api_key=None, # Anam API key (or set ANAM_API_KEY env var)
client_options=None, # Optional Anam ClientOptions for advanced configuration
connect_timeout=None, # Seconds to wait for connection (None = wait indefinitely)
session_ready_timeout=None, # Seconds to wait for session ready (None = wait indefinitely)
width=1920, # Output video width in pixels
height=1080, # Output video height in pixels
)
How It Works
- Anam Connection: Connects to Anam's avatar service and waits for the session to become ready
- Audio Forwarding: TTS audio from the agent is resampled to 24kHz mono and streamed to Anam
- Avatar Generation: Anam generates synchronized avatar video and lip-synced audio from the input
- Video Streaming: Avatar video and audio frames are streamed back to call participants via GetStream Edge
Requirements
- Python 3.10+
- Anam API key and avatar ID (get them at anam.ai)
- GetStream account for video calls
- TTS provider (ElevenLabs, Cartesia, etc.) or Realtime LLM
License
MIT
Links
Metadata
Release files for vision-agents-plugins-anam 0.6.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| vision_agents_plugins_anam-0.6.9.tar.gz | 5.7 kB | Without provenance | Details for vision_agents_plugins_anam-0.6.9.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vision_agents_plugins_anam-0.6.9-py3-none-any.whl | Python 3 | none | any | Details for vision_agents_plugins_anam-0.6.9-py3-none-any.whl |
Total release size: 11.6 kB
Release files / vision_agents_plugins_anam-0.6.9.tar.gz
| Download URL | vision_agents_plugins_anam-0.6.9.tar.gz |
|---|---|
| Size | 5.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1cf018998b45149173cb578aed273af97bc2bc468639c270cb51748c0b581595
|
|
BLAKE2b-256 checksum How to use checksums |
8da3ec124b292418c0b8fcc9ffb337dc2b41e040348a3ffba4a6ce89c4a553b2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / vision_agents_plugins_anam-0.6.9-py3-none-any.whl
| Download URL | vision_agents_plugins_anam-0.6.9-py3-none-any.whl |
|---|---|
| Size | 5.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
227360abcb50dacfb272083c8b31795493bbf072cd02c3bbc993fc0a53efc0b9
|
|
BLAKE2b-256 checksum How to use checksums |
b2bd4cbcbd653d7e9704322ef2fc4103c1aaa05153359cc5b44bfd4f60f1ed0e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for vision-agents-plugins-anam 0.6.9
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.