Create Engaging Conversational Voices with lucataco/pheme Cognitive Actions

23 Apr 2025
Create Engaging Conversational Voices with lucataco/pheme Cognitive Actions

In today's digital landscape, the ability to generate natural and engaging conversational voices is essential for enhancing user experiences in applications, especially for voice-based interactions. The lucataco/pheme API offers a powerful Cognitive Action called Generate Conversational Voices, which leverages the Pheme TTS (Text-to-Speech) framework to produce high-quality, conversational audio optimized for phone-call applications. This article will guide you through using this action, detailing its capabilities, input requirements, and how to implement it in your applications.

Prerequisites

Before you start using the Cognitive Actions in the lucataco/pheme API, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform. This key will be passed in the headers of your requests for authentication.
  • Basic knowledge of making HTTP requests in your programming language of choice (e.g., Python).

Cognitive Actions Overview

Generate Conversational Voices

The Generate Conversational Voices action is designed to produce a variety of high-quality, conversational audio outputs optimized for phone-call applications. This action emphasizes efficiency in data processing while maintaining exceptional single-speaker audio quality through innovative training techniques.

Input

The input for this action is structured as follows, with required and optional parameters:

  • topK: (integer, default: 210) Specifies the number of top results to return. Must be between 10 and 250, inclusive.
  • inputPrompt: (string, default: "I gotta say, I would never expect that to happen!") The input text prompt that provides context for the speech synthesis.
  • voiceSelection: (string, default: "male_voice") The voice to use for the output. Options include 'male_voice' and various specific identifiers.
  • responseTemperature: (number, default: 0.7) Controls the randomness of responses, with values ranging from 0.3 to 1.5.

Example Input JSON:

{
  "topK": 210,
  "inputPrompt": "I gotta say, I would never expect that to happen!",
  "voiceSelection": "POD0000004393_S0000029",
  "responseTemperature": 0.7
}

Output

Upon successful execution, the action returns a link to the generated audio file. The output typically looks like this:

Example Output:

https://assets.cognitiveactions.com/invocations/6d434072-8648-4e47-ae65-5fcda7b6d186/2b20329f-7ddc-416a-8eda-5e4b195478a7.wav

Conceptual Usage Example (Python)

Here’s a conceptual example of how to invoke the Generate Conversational Voices 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 = "bea543f7-db25-43d8-888c-14ca3abd947d"  # Action ID for Generate Conversational Voices

# Construct the input payload based on the action's requirements
payload = {
    "topK": 210,
    "inputPrompt": "I gotta say, I would never expect that to happen!",
    "voiceSelection": "POD0000004393_S0000029",
    "responseTemperature": 0.7
}

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 will need to replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action ID for Generate Conversational Voices is specified, and the input payload is structured according to the defined schema. The response is printed, allowing you to access the generated audio link easily.

Conclusion

The Generate Conversational Voices action from the lucataco/pheme API provides developers with an exciting opportunity to enhance their applications with high-quality, conversational audio. By integrating this Cognitive Action, you can create more engaging user interactions, particularly in voice-based applications. As a next step, consider exploring different voice selections and adjusting the response temperature to see how it affects the generated audio output. Happy coding!

← Back to All Articles