Unlocking Voice Cloning Potential with OpenVoice Cognitive Actions

In the realm of voice synthesis and manipulation, the OpenVoice API from chenxwh/openvoice stands out by providing advanced capabilities for instant voice cloning. With pre-built Cognitive Actions, developers can leverage these features to create applications that require high-quality, multi-lingual voice outputs. This guide will walk you through one of the key actions available, giving you the knowledge to seamlessly integrate it into your own projects.

Prerequisites

Before diving into the Cognitive Actions, ensure you have:

• An API key for the Cognitive Actions platform to authenticate your requests.
• Basic familiarity with JSON and Python for constructing requests and handling responses.

Authentication typically involves passing your API key in the headers of your requests.

Cognitive Actions Overview

Perform Versatile Instant Voice Cloning

This action utilizes OpenVoice V2 to perform advanced voice cloning, enabling developers to generate audio that mimics a reference voice while maintaining high audio quality and supporting multiple languages. The capability for zero-shot cross-lingual cloning allows for versatile applications in various linguistic contexts.

Input

The input for this action is structured in a JSON object that requires the following fields:

• audio (string): The URI of the input reference audio file. This field is required.
• text (string): The input text for processing. Default text is "Did you ever hear a folk tale about a giant turtle?".
• speed (number): The speed scale of the output audio, defaulting to 1.
• audioLanguage (string): The language of the generated audio, with options including EN_NEWEST, EN, ES, FR, ZH, JP, and KR. The default is EN_NEWEST.

Example Input:

{
  "text": "Did you ever hear a folk tale about a giant turtle?",
  "audio": "https://replicate.delivery/pbxt/KpK4hkLwhVAJE9K0DAbZP3YfwLzJyLl09kuPnc4MvCYLcX8m/example_reference.mp3",
  "speed": 1,
  "audioLanguage": "EN_NEWEST"
}

Output

The output of this action is a URI pointing to the generated audio file. This file will contain the cloned voice output based on the provided reference.

Example Output:

https://assets.cognitiveactions.com/invocations/f98adafc-ba35-4bef-854c-f723d3eb52fe/2c0dfbec-b5d5-4f01-bc84-9fde2057fa3d.wav

Conceptual Usage Example (Python)

Here’s how you could structure a request to execute this action using Python:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute" # Hypothetical endpoint

action_id = "475f0152-bd5e-4339-9b6f-1115c0e4fbf3" # Action ID for Perform Versatile Instant Voice Cloning

# Construct the input payload based on the action's requirements
payload = {
    "text": "Did you ever hear a folk tale about a giant turtle?",
    "audio": "https://replicate.delivery/pbxt/KpK4hkLwhVAJE9K0DAbZP3YfwLzJyLl09kuPnc4MvCYLcX8m/example_reference.mp3",
    "speed": 1,
    "audioLanguage": "EN_NEWEST"
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload} # Hypothetical structure
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this code snippet, you'll notice that the action ID and input payload are structured to match the requirements of the Perform Versatile Instant Voice Cloning action. The endpoint URL and request format are illustrative and may vary based on actual implementation.

Conclusion

The OpenVoice Cognitive Actions provide a powerful toolset for developers looking to incorporate advanced voice cloning features into their applications. By utilizing the Perform Versatile Instant Voice Cloning action, you can create engaging and customized audio experiences across multiple languages and styles. Explore these capabilities and consider what innovative solutions you can build!