How to generate voices with Python?

How to generate voices with Python?

·

3 min read

In this tutorial, you will learn how to use Text-to-speech API in 5 minutes with Python. Eden AI provides an easy and developer-friendly API that allows you to use voice generators.

What is Text-to-speech / Voice generation?

Text-to-Speech (TTS) technology can seamlessly transforms written text into natural-sounding speech. By employing sophisticated algorithms and artificial intelligence, TTS systems analyze the linguistic structure of the text and generate lifelike speech output. TTS technology has evolved to produce highly expressive voices, incorporating elements like intonation, pronunciation, and speech rate adjustments to create a more human-like and engaging audio experience.

Text-to-Speech result on Eden AI

This advancement enables visually impaired individuals to access written content and enhances the user experience across various domains such as e-learning, assistive technology, audiobook production, navigation systems, and voice assistants.

Get Started with Text-to-speech API

The first step is to install Python's requests package, that will allow you to call Eden AI API.

Image description

Next, you'll need to install Python's JSON package in order to read and print the result of the API request.

Image description

How to use Text-to-speech API with Python

1. Get a Text-to-speech API Key on Eden AI

To perform Text-to-speech, you'll need to create an account on Eden AI for free. Then, you will be able to get your API key directly from the homepage with free credits offered by Eden AI.

Image description

Get your API key for FREE

2. Let’s generate voices

Once you have imported packages on Python and got your API key, you will be able to generate speech with text. You can access the list of Text-to-speech engines available on Eden AI to help you choose the provider that best suits your project and needs.

Here is the Python script you need to write in your notebook:

https://uploads-ssl.webflow.com/61e7d259b7746e3f63f0b6be/64625808a4a51e59e1ac70c0_carbon(81).png

For example, we called two different Text-to-Speech engines. Eden AI API will then return in its JSON response results of those providers.

Once the request is done, you will be able to get the result with this print:

https://uploads-ssl.webflow.com/61e7d259b7746e3f63f0b6be/64625812de766711926096e4_carbon(82).png

Here is an example of a Text-to-speech API response:

https://uploads-ssl.webflow.com/61e7d259b7746e3f63f0b6be/6462586a76d40d255395475d_carbon(94).png

Benefits of using Text-to-speech API with Eden AI

Using Text-to-speech with Eden AI API is quick and easy.

Multiple AIs in one API - Eden AI

Save time and cost

We offer a unified API for all providers: simple and standard to use, with a quick switch between providers and an access to the specific features of each provider.

Easy to integrate

The JSON output format is the same for all suppliers thanks to Eden AI's standardisation work. The response elements are also standardised thanks to Eden AI's powerful matching algorithms.

Customization

With Eden AI you have the possibility to integrate a third-party platform: we can quickly develop connectors. To go further and customize your Text-to-speech request with specific parameters, check out our documentation.

Create your Account on Eden AI