معرفی و مستندات مدل هوش مصنوعی vibevoice-1.5b

import os
import requests

def main():
    url = "https://api.ai-kar.com/v1/tts"
    headers = {
        "Authorization": "Bearer <YOUR_AI-KARAPI_KEY>",
    }
    payload = {
        "model": "microsoft/vibevoice-1.5b",
        "script": "Speaker 1: Wow, whats happening, Alice? \nSpeaker 2: Oh, just the usual… a full-blown AI revolution. Nothing to worry about",
        "speakers": [
            {
                "preset": "Frank [EN]"
            },
            {
                "preset": "Alice [EN]"
            }
        ]
    }
    try:
        response = requests.post(url, headers=headers, json=payload)
        response.raise_for_status()
        response_data = response.json()
        audio_url = response_data["audio"]["url"]
        file_name = response_data["audio"]["file_name"]
        audio_response = requests.get(audio_url, stream=True)
        audio_response.raise_for_status()
        # Save with the original file extension from the API
        # dist = os.path.join(os.path.dirname(__file__), file_name)  # if you run this code as a .py file
        dist = "audio.wav"  # if you run this code in Jupyter Notebook
        with open(dist, "wb") as write_stream:
            for chunk in audio_response.iter_content(chunk_size=8192):
                if chunk:
                    write_stream.write(chunk)
        print("Audio saved to:", dist)
        print(f"Duration: {response_data['duration']} seconds")
        print(f"Sample rate: {response_data['sample_rate']} Hz")
    except requests.exceptions.RequestException as e:
        print(f"Error making request: {e}")
    except Exception as e:
        print(f"Error: {e}")


if __name__ == "__main__":
    main()

{
  "metadata": {
    "transaction_key": "text",
    "request_id": "text",
    "sha256": "text",
    "created": "2025-11-24T16:42:22.099Z",
    "duration": 1,
    "channels": 1,
    "models": [
      "text"
    ],
    "model_info": {
      "ANY_ADDITIONAL_PROPERTY": {
        "name": "text",
        "version": "text",
        "arch": "text"
      }
    }
  }
}