Transform Text into Speech: Integrating Multilingual Capabilities with ttsds/parlertts_mini_multilingual Cognitive Actions

23 Apr 2025
Transform Text into Speech: Integrating Multilingual Capabilities with ttsds/parlertts_mini_multilingual Cognitive Actions

In today's digital landscape, the ability to convert text into speech across multiple languages is a game-changer for applications aiming to enhance user engagement and accessibility. The ttsds/parlertts_mini_multilingual API provides developers with powerful Cognitive Actions that enable high-quality voice output in various languages. By leveraging these pre-built actions, you can seamlessly integrate multilingual text-to-speech capabilities into your applications, enhancing user interaction and broadening your audience reach.

Prerequisites

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

  • API Key: You'll need an API key for the Cognitive Actions platform to authenticate your requests.
  • Basic Setup: Familiarity with making HTTP requests in your programming language of choice is essential. The API typically requires authentication via an API key passed in the request headers.

Cognitive Actions Overview

Generate Multilingual Audio

The Generate Multilingual Audio action allows you to convert text into high-quality multilingual speech using the ParlerTTS Mini model. This action is particularly useful for applications that require voice synthesis in various languages, making it a vital tool for global applications.

Input

The input schema for this action is as follows:

  • text (required): The main body of text content that will be processed.
  • prompt (optional): An optional prompt to guide or influence responses related to the text.
  • textReference (optional): A string providing additional reference context for the text, if applicable.
  • speakerReference (optional): A URI pointing to an audio reference for the speaker if needed.

Example Input:

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

Output

The typical output of this action is a URL pointing to the generated audio file. The audio file will contain the spoken version of the provided text.

Example Output:

https://assets.cognitiveactions.com/invocations/7b074532-a2bc-4df9-9c8e-289754af509c/2ad0c82c-013d-49f3-9ca1-7aea6d84d8a7.wav

Conceptual Usage Example (Python)

Here’s a conceptual example of how you can use the Generate Multilingual Audio action in 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 = "1d9c424d-3914-4887-8da5-257756928cc1" # Action ID for Generate Multilingual Audio

# 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.",
    "prompt": "",
    "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 example, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id corresponds to the Generate Multilingual Audio action, and the payload is structured according to the required input schema. The code attempts to make a POST request to the hypothetical Cognitive Actions endpoint, handling any potential errors gracefully.

Conclusion

The ttsds/parlertts_mini_multilingual Cognitive Actions provide a robust solution for integrating multilingual text-to-speech capabilities into your applications. By utilizing the Generate Multilingual Audio action, developers can enhance user experiences through high-quality voice outputs in diverse languages. Consider exploring additional use cases, such as creating audiobooks, enhancing accessibility for visually impaired users, or adding voice features to chatbots. Start integrating these powerful actions today and elevate your application's engagement!

← Back to All Articles