Simple Text to Speech

Simple Text to Speech is a small and easy to use text to speech (TTS) WordPress plugin that uses AI to generate audio versions of your posts and pages.

The plugin supports more than 50 languages and seamlessly integrates with the WordPress Block Editor but it also supports the good old Classic editor.

When the audio has been generated for a post or a page from the Block editor sidebar, an audio player will be displayed automatically at the top of your page, which visitors can listen to. You can also upload audio files from external sources, enabling you to use real human voices if you want. The audio files will appear on top of the page, improving accessibility and user engagement.

Features

• Block Editor Integration – Generate audio directly from the post/page editor from the sidebar panel
• AI Voices – Use Google’s WaveNet voices for natural-sounding speech
• Multiple Languages – Supports over 50 languages and variants
• Accessibility ready – Improves content accessibility by providing audio versions of your posts and pages
• Automatic Storage – Audio files are automatically saved to your WordPress Media Library
• Easy Management – Delete audio files from either the editor panel or the Media Library
• Custom audio upload – Ability to upload audio from external sources and use real human voices
• Multi-language Support – Supports 50+ languages and language variants

How It Works

1. Configure your Google Cloud API key in Settings > Text to Speech
2. Edit any post or page in the Block Editor
3. Find the “Text to Speech” panel in the document sidebar
4. Click “Generate Audio” to create an MP3 file from your content
5. Audio is saved to Media Library and attached to the post
6. Play, download, or delete audio directly from the panel

Google Cloud Text-to-Speech

This plugin uses Google Cloud Text-to-Speech API, which requires an API key. Google offers a generous free tier: * WaveNet voices: 1 million characters per month free * Standard voices: 4 million characters per month free

This plugin uses predominantly WaveNet AI voices, as well as Standard AI voices when WaveNet voices are not available for the specific language.

Learn more about Google Cloud Text-to-Speech pricing.