In the previous graphic tutorial, we shared the detailed steps of account application and API application for Azure machine learning text-to-speech , and also introduced the code implementation process of Azure machine learning text-to-speech function based on python3 , although we can use Azure account for free A one-year trial period is provided, but we have to pay after all, and our API cannot be used for a long time. Fortunately, Microsoft has released the edge-tts library, which inherits the text-to-speech function of Azure and is free to use. In this period, we will introduce the use of edge-tts. Maybe you hear the generated sound below, and you find it very familiar.
Edge-TTS is a Python library that implements text-to-speech (TTS) using Microsoft's Azure Cognitive Services. This library provides a simple API to convert text to speech, and supports multiple languages and voices. To use the Edge-TTS library, you first need to install the Edge-TTS library, and you can install it directly with pip.
pip install edge-ttsThe code for this issue here is based on