A simple, easy-to-use web interface for generating high-quality audio from text using OpenAI's Text-to-Speech (TTS) API. This tool allows you to input text, select a voice, and download the resulting audio in various formats.
- Simple Interface: Clean and intuitive UI built with Tailwind CSS.
- High-Quality Audio: Uses the
tts-1-hdmodel for high-definition audio. - Instruction Templates: Choose from pre-defined instruction templates (e.g., Patient Teacher, Chill Surfer, Medieval Knight) to guide the voice's tone and cadence.
- Custom Instructions: Write your own detailed instructions for the voice model.
- Voice Selection: Choose from all available voices: Alloy, Ash, Ballad, Coral, Echo, Fable, Nova, Onyx, Sage, and Shimmer.
- Multiple Formats: Download the generated audio in MP3, OPUS, AAC, or FLAC.
- API Key Management: Your API key is saved locally in your browser's
localStoragefor convenience. - Audio Preview: Listen to the generated audio directly in the browser before downloading.
- Responsive Design: Works on both desktop and mobile devices.
You need a modern web browser and an API key from OpenAI.
- Clone the repository:
git clone [https://github.com/your-username/your-repo-name.git](https://github.com/your-username/your-repo-name.git)
- Navigate to the project directory:
cd your-repo-name - Open
index.html: Simply open theindex.htmlfile in your web browser. There are no build steps or dependencies to install.
- Open
index.htmlin your browser. - Enter your OpenAI API Key in the input field.
- (Optional) Select an instruction template or write your own custom instructions.
- Enter the text you want to convert to speech.
- Select the desired voice and output format.
- Click "Generate Audio".
- The audio will be generated and you can preview it or download the file.
Contributions, issues, and feature requests are welcome! Feel free to check the issues page.
This project is licensed under the MIT License. See the LICENSE file for details.