設定即時虛擬化身

import asyncio
import json
import websockets

# Replace PROJECT_ID and LOCATION with your Project ID and location.
PROJECT_ID = "PROJECT_ID"
LOCATION = "LOCATION"

# Authentication
token_list = !gcloud auth application-default print-access-token
ACCESS_TOKEN = token_list[0]

# Configuration
MODEL_ID = "gemini-3.8-live"
MODEL = f"projects/{PROJECT_ID}/locations/{LOCATION}/publishers/google/models/{MODEL_ID}"

config = {
    "response_modalities": ["VIDEO"],
    "speech_config": {
        "voice_config": {
            "prebuilt_voice_config": {
                "voice_name": "Puck",
            }
        }
    },
}

avatar_config = {
    "avatar_name": "Ben",
}

# Construct the WSS URL
HOST = f"{LOCATION}-aiplatform.googleapis.com"
URI = f"wss://{HOST}/ws/google.cloud.aiplatform.v1.LlmBidiService/BidiGenerateContent"

async def main():
    headers = {"Authorization": f"Bearer {ACCESS_TOKEN}"}

    async with websockets.connect(URI, additional_headers=headers) as ws:
        print("Session established.")

        # Send Setup (Handshake)
        await ws.send(json.dumps({
            "setup": {
                "model": MODEL,
                "generation_config": config,
                "avatar_config": avatar_config,
            }
        }))
        # Send and receive audio/video streams...

if __name__ == "__main__":
    asyncio.run(main())

from google import genai
from google.genai import types

client = genai.Client()

config = types.LiveConnectConfig(
    response_modalities=["VIDEO"],
    speech_config=types.SpeechConfig(
        voice_config=types.VoiceConfig(
            prebuilt_voice_config=types.PrebuiltVoiceConfig(
                voice_name="Puck",
            )
        )
    ),
    avatar_config=types.AvatarConfig(
        avatar_name="Ben",
    ),
    system_instruction=types.Content(
        parts=[types.Part.from_text(text="You are a helpful customer service assistant.")]
    ),
)

async with client.aio.live.connect(model="gemini-3.8-live", config=config) as session:
    # Interact with the live session...
    pass

import base64
import json
import websockets

# Load custom avatar image (PNG format, 704x1280 min)
with open("/path/to/your/sample_avatar.png", "rb") as f:
    avatar_b64 = base64.b64encode(f.read()).decode("utf-8")

GENERATION_CONFIG = {
    "response_modalities": ["VIDEO"],
}

# Setup avatar config with custom face image
AVATAR_CONFIG = {
    "customized_avatar": {
        "image_data": avatar_b64,
        "image_mime_type": "png",
    }
}

# Session setup message
SETUP_MESSAGE = {
    "setup": {
        "model": "gemini-3.8-live",
        "generation_config": GENERATION_CONFIG,
        "avatar_config": AVATAR_CONFIG,
        "system_instruction": {
            "parts": [{"text": "Your system instruction here"}]
        },
        "input_audio_transcription": {},
        "output_audio_transcription": {},
    }
}