EasyTTS

EasyTTS

Introduction

EasyTTS is a convenient tool designed to easily use third-party API services to invoke OpenAI's text-to-speech (TTS) functionality.
EasyTTS allows users to enter text and select different models, voices, and formats to generate audio files. The code for this project is almost entirely written by GPT-4 and I only provide requirements and suggestions.
Before using this tool, you should obtain an API-KEY that can call OpenAI TTS.

Known API service providers that support calling OpenAI TTS (replacement is welcome)

ChatAnywhere (only paid key supports calling OpenAI TTS, please select "Support paid key" to get API-KEY)
Bltcy

Start quickly

Before you start using it, make sure that Python is installed on your computer. If you have not installed Python yet, you can go to the Python official website to download and install it.

Installation steps

1. Clone or download this project to your local computer. If you are accessing through GitHub, you can click the green "Code" button on the interface, then click "Download ZIP", and unzip it after the download is completed.
2. Double-click the安装所需的Python库.bat to install the required Python library (such as inquirer ).
3. Double-click Run日常启动.bat and select "Update API Setup" in the launcher menu to enter your API key and API base address.

How to use

1. Double-click to run日常启动.bat file.
2. In the launcher menu, select Main Program to start the text to voice program.
3. Follow the prompts on the screen to enter text, select audio quality, sound options, and audio format.
4. Enter a file name (no extension required), and the program will generate the corresponding audio file and save it in a folder named "File" in the same directory as this project.

Things to note

• Make sure your API key and API base address are correct and available. If the request is not successful when running the main program to obtain the audio file, please contact the API service provider you selected for support.

Tone

To learn about each tone, please visit Text to Speech - OpenAI API. Note that the same tone may differ in different languages, please refer to the actual effect.
You can also find videos about ChatGPT voice dialogue functions on major video websites. The voice dialogue function in OpenAI's ChatGPT APP uses OpenAI TTS.

Features being tried to add

WebUI
Tone display (bilingual)
API consumption, balance query

contribute

Welcome to contribute to the project! If you have any suggestions or want to add new features, feel free to create an Issue or Pull Request.