Vibevoice 7b

This documentation is valid for the following list of our models:

• microsoft/vibevoice-7b

Try in Playground

Designed to produce rich, multi-speaker conversations from text, the model is well-suited for podcasts and other long-form audio content. The 7-billion-parameter version of the model.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post

Body

modelstring · enumRequiredPossible values:

scriptstring · min: 1 · max: 5000Required

The script to convert to speech. Can be formatted with "Speaker X:" prefixes for multi-speaker dialogues.

seedintegerOptional

If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed.

cfg_scalenumber · min: 0.1 · max: 2Optional

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt.

Default: 1.3

streamboolean · enumOptionalDefault: falsePossible values:

Responses

200Success

audiostring · uriRequired

post/v1/tts

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/tts' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
      "model": "microsoft/vibevoice-7b",
      "script": "Cities of the future promise to radically transform how people live, work, and move. Instead of sprawling layouts, we will see vertical structures that integrate residential, work, and public spaces into single, self-sustaining ecosystems. Architecture will adapt to climate conditions, and buildings will be energy-efficient—generating power through solar panels, wind turbines, and even foot traffic."
    }'

200Success

{
  "audio": "https://example.com",
  "meta": {
    "usage": {
      "credits_used": 120000,
      "usd_spent": 0.06
    }
  }
}

Code Example

Python

import os
import requests

def main():
    url = "https://api.aimlapi.com/v1/tts"
    headers = {
        "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
    }
    payload = { 
        "model": "microsoft/vibevoice-7b",
        "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()

Response

Audio saved to: audio.wav
Duration: 7.866666666666666 seconds
Sample rate: 24000 Hz