Master Voice Cloning with the ttsds/amphion_vevo Cognitive Actions

22 Apr 2025
Master Voice Cloning with the ttsds/amphion_vevo Cognitive Actions

In the realm of artificial intelligence, voice cloning has emerged as a powerful technology, enabling applications from personalized virtual assistants to engaging multimedia content. The ttsds/amphion_vevo Cognitive Actions provide developers with a simple yet effective way to integrate voice imitation capabilities into their applications. These pre-built actions utilize the Vevo model by Amphion, allowing for controllable zero-shot voice replication through self-supervised disentanglement. In this post, we will explore the features of the "Perform Voice Imitation with Vevo" action and how to effectively use it in your projects.

Prerequisites

Before you get started with the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform, which authorizes your requests.
  • Basic understanding of JSON structure and HTTP requests, as you will be sending and receiving JSON data.

To authenticate your requests, you will typically include the API key in the headers of your HTTP calls.

Cognitive Actions Overview

Perform Voice Imitation with Vevo

The Perform Voice Imitation with Vevo action allows you to replicate a speaker's voice using a provided audio reference. This is particularly useful for applications requiring customized voice outputs in various languages.

  • Category: voice-cloning

Input

The input for this action must follow the specified schema:

  • text: The content you want to convert to speech. (Required)
  • language: The language code for the speech output. (Required)
  • speakerReference: A URI pointing to the audio file that serves as a reference for the speaker's voice. (Required)

Example Input:

{
  "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
  "language": "en",
  "speakerReference": "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
}

Output

When the action is executed successfully, it returns a URI linking to the generated audio file of the imitation. Here’s an example of what that output might look like:

Example Output:

https://assets.cognitiveactions.com/invocations/d17c13ec-c3ae-4670-b855-4856606ef480/04e73a6c-2df1-47c5-99b7-e9d1f7c9b11f.wav

Conceptual Usage Example (Python)

Here’s how you can call the Perform Voice Imitation with Vevo 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 = "ef46d9fb-24d2-44a5-a3ad-e7abea496a87"  # Action ID for Perform Voice Imitation with Vevo

# Construct the input payload based on the action's requirements
payload = {
    "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
    "language": "en",
    "speakerReference": "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
}

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 Python snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action ID for Perform Voice Imitation with Vevo is included, and the input payload is structured to match the required schema. The endpoint URL is hypothetical and should be replaced with the actual endpoint provided by your Cognitive Actions service.

Conclusion

The ttsds/amphion_vevo Cognitive Action for voice imitation offers developers a powerful tool to create voice outputs that sound natural and personalized. By leveraging the Vevo model, you can bring your applications to life with customized voice interactions. Whether you are developing a virtual assistant, creating engaging multimedia content, or exploring innovative voice applications, these Cognitive Actions can pave the way for enhanced user experiences.

Explore the capabilities of voice cloning today and consider integrating this action into your next project!

← Back to All Articles