Unlocking Voice with Text-to-Speech Using ttsds/gptsovits_1 Cognitive Actions

23 Apr 2025
Unlocking Voice with Text-to-Speech Using ttsds/gptsovits_1 Cognitive Actions

In the realm of application development, the ability to convert text into natural-sounding speech can significantly enhance user engagement and accessibility. The ttsds/gptsovits_1 Cognitive Actions provide developers with the tools to seamlessly integrate Text-to-Speech capabilities into their applications. By leveraging pre-built actions, developers can save time and resources while delivering high-quality voice experiences.

Prerequisites

Before diving into the integration of Cognitive Actions, ensure you have the following:

  • API Key: You will need an API key for the Cognitive Actions platform to authenticate your requests.
  • Setup: Familiarize yourself with sending HTTP requests and handling JSON payloads. The API key is typically passed in the request headers for authentication.

Cognitive Actions Overview

Perform Text-to-Speech Prediction

The Perform Text-to-Speech Prediction action generates a speech prediction based on the provided input text and language code, utilizing a speaker reference for voice matching. This action falls under the text-to-speech category and is ideal for applications that aim to deliver dynamic audio content.

Input

The input for this action is structured according to the schema defined below:

  • languageCode (required): Specifies the language of the text. Possible values are:
    • en for English
    • zh for Chinese
    • ja for Japanese
  • speakerReference (required): A URI pointing to an audio file with a sample of the speaker's voice for matching.
  • text (required): The main body of text to be processed. It should be a complete sentence or passage.
  • textReference (optional): Reference text or additional context related to the main text, typically a phrase or excerpt.

Here’s an example of how the input might look:

{
  "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
  "languageCode": "en",
  "textReference": "and keeping eternity before the eyes, though much.",
  "speakerReference": "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
}

Output

The action typically returns a URL pointing to the generated audio file. For instance:

https://assets.cognitiveactions.com/invocations/af40796d-5bba-4b2a-96d8-a535128175cd/7e6e4565-fc1c-47e8-beb5-a337c97272af.wav

This URL can be used to access the synthesized speech output.

Conceptual Usage Example (Python)

Below is a conceptual example of how to call the Perform Text-to-Speech Prediction action using Python. This snippet demonstrates how to structure your request payload and make the API call.

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 = "bed92271-7951-4cf3-8df3-e6fc342a2809"  # Action ID for Perform Text-to-Speech Prediction

# 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.",
    "languageCode": "en",
    "textReference": "and keeping eternity before the eyes, though much.",
    "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 code snippet:

  • Replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • The payload is structured according to the action’s input schema.
  • The response is parsed to retrieve the output URL for accessing the generated speech.

Conclusion

The ttsds/gptsovits_1 Cognitive Actions provide a powerful way to integrate Text-to-Speech functionality into your applications. By utilizing the Perform Text-to-Speech Prediction action, developers can enhance user experiences through dynamic audio outputs. Explore the potential of these actions in your projects and consider how they can be tailored to meet your specific use cases. Happy coding!

← Back to All Articles