How to Use Text-to-Speech (TTS)

The Text-to-Speech (TTS) feature transforms written content into natural-sounding spoken audio. Whether you’re creating audio versions of documents, voiceovers, or accessibility content, this guide will help you get started.

Getting Started

• Click Create New Project and select Text-to-Speech.
• Give your project a name for easy reference.

Enter or Upload Text

You can provide your content in one of two ways:

• Type or paste your text directly into the text editor.
  
• Or, upload a text file to import your content automatically.

Choose Preferences

Before generating audio:

• Select the source language (original language of the text).
• Choose the target language (language for translation).
• Choose a voice from the available options.
• Agree to the terms by ticking the checkbox.
• Click Generate to start processing the text into speech.

Download Output

After processing is complete:

• Preview the audio, if needed.
• Click Download to save the processed audio file to your device.

Best Practices for Text-to-Speech

To ensure the best audio quality:

• Use grammatically correct text.
• Stick to one language per input—avoid mixing languages in a single file.
• Check for proper spelling and punctuation before generating.

Text File Requirements

• Supported file types: .txt, .doc

Credits and Limits: