How to Use the Text to Sound Effects API

​

Introduction

Our text to sound effects model enables you to create high-quality sound effects from a short description. These sound effects could be used in a variety of applications, including game development and building apps for music production.

In this tutorial, we will use the text to sound effects API to generate a sound effect from a short description using the Python SDK. We’ll then save this sound effect to a file.

​

How to generate a sound effect with the API

​

Requirements

Before proceeding, please ensure that you have the following:

• An ElevenLabs account with an API key (here’s how to find your API key)
• Python or Node.js installed on your machine

Then, install the ElevenLabs SDK as shown below

Install the necessary packages to manage your environmental variables:

Next, create a .env file in your project directory and fill it with your credentials like so:

ELEVENLABS_API_KEY=your_elevenlabs_api_key_here

​

Using the sound effects SDK

Now we can use the SDK to generate a sound effect from a short description and save it to a file as shown below.

import os
from elevenlabs.client import ElevenLabs

from dotenv import load_dotenv

load_dotenv()

elevenlabs = ElevenLabs(api_key=os.getenv("ELEVENLABS_API_KEY"))


def generate_sound_effect(text: str, output_path: str):
    print("Generating sound effects...")

    result = elevenlabs.text_to_sound_effects.convert(
        text=text,
        duration_seconds=10,  # Optional, if not provided will automatically determine the correct length
        prompt_influence=0.3,  # Optional, if not provided will use the default value of 0.3
    )

    with open(output_path, "wb") as f:
        for chunk in result:
            f.write(chunk)

    print(f"Audio saved to {output_path}")


if __name__ == "__main__":
    generate_sound_effect("Dog barking", "output.mp3")

​

Configuration

• duration_seconds: The duration of the sound effect in seconds. If not provided, the API will automatically determine the correct length. The maximum value is 22
• prompt_influence: The amount of influence the prompt has on the generated sound effect. If not provided, the API will use the default value of 0.3

​

API pricing

The API is charged at 100 characters per generation with automatic duration or 25 characters per second with a set duration.

​

Next steps

We’re excited to see what you build with the API. Here are some ideas of what you might want to use it for:

• Adding sound effect generation to a video editing application
• Enabling users to create on-demand samples for their music production
• A new type of video game where every sound is generated dynamically

For higher rate limits of volume based discounts please contact sales.