text-to-speech

Create Natural-Sounding Speech with Parler TTS

27 Apr 2025
Create Natural-Sounding Speech with Parler TTS

In today's digital landscape, the demand for high-quality, natural-sounding speech synthesis is rapidly increasing. Enter Parler TTS, a powerful text-to-speech service that leverages advanced AI technology to transform written text into lifelike audio. This service is particularly beneficial for developers looking to enhance user experiences in applications, websites, and content creation tools. With customizable features such as gender, background noise, speaking rate, pitch, and reverberation, Parler TTS allows for a tailored auditory experience that can engage users more effectively.

Common use cases for Parler TTS include creating voiceovers for educational content, generating audio for virtual assistants, enhancing accessibility for visually impaired users, and producing dynamic audio responses for chatbots. By integrating Parler TTS into your projects, you can simplify audio production while ensuring a high level of quality and customization.

Prerequisites

To get started with Parler TTS, you'll need a valid Cognitive Actions API key and a fundamental understanding of making API calls.

Generate Speech with Parler-TTS Mini

The "Generate Speech with Parler-TTS Mini" action allows developers to utilize the Parler-TTS Mini v0.1 model to convert text into high-quality, natural-sounding speech. This action focuses on delivering audio that is both expressive and nuanced, thanks to its training on 10.5K hours of audio data. By using specific prompts, developers can achieve precise control over the audio output, making it ideal for a variety of applications.

Input Requirements

The input for this action consists of a JSON object with two key properties:

  • prompt: The text that will be converted into speech. This should reflect the intended tone and clarity of the audio.
  • description: A detailed outline of the desired audio attributes, including voice characteristics and the speaking environment.

Example Input:

{
  "prompt": "Remember - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
  "description": "A male speaker with a low-pitched voice delivering his words at a fast pace in a small, confined space with a very clear audio and an animated tone."
}

Expected Output

The expected output is a URL link to an audio file generated from the provided text, which will reflect the specified audio characteristics.

Example Output:

https://assets.cognitiveactions.com/invocations/38dabf30-ed95-4b56-97e8-d1b17251cde8/3ad696b9-62c5-4e8c-a54c-664ad780afca.wav

Use Cases for this Specific Action

This action is particularly useful in scenarios where personalized, context-aware audio is required. For instance:

  • E-Learning Platforms: Generate engaging audio lectures that can cater to different learning styles.
  • Virtual Assistants: Create responsive and natural-sounding voice outputs to improve user interaction.
  • Accessibility Tools: Enhance the user experience for individuals with visual impairments by providing clear and expressive audio feedback.
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "238adfab-c58f-496e-bab0-b04410934f2d" # Action ID for: Generate Speech with Parler-TTS Mini

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "prompt": "Remember - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
  "description": "A male speaker with a low-pitched voice delivering his words at a fast pace in a small, confined space with a very clear audio and an animated tone."
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")

Conclusion

Integrating Parler TTS into your applications can significantly enhance user engagement and accessibility through high-quality speech synthesis. With its customizable features and ease of use, developers can create tailored audio experiences that resonate with their audience. As you explore the capabilities of Parler TTS, consider the various applications it can support, from e-learning to virtual assistants, and take the next steps in elevating your projects with lifelike audio.

← Back to All Articles