Speaker is a powerful text-to-speech (TTS) plugin that allows you to automatically convert web content into human-like audio, enhancing accessibility and giving users a new way to consume content for blogs, news sites, and educational portals.

Key Features

• Uses Google Cloud Text-to-Speech, offering 600+ realistic AI voices in 45+ languages and dialects.
• Includes male and female voices, accents, and different speaking styles (e.g., newscaster, conversational, etc.).
• Supports SSML (Speech Synthesis Markup Language) for more advanced audio control (pauses, pitch, speed).
• Customize reading speed, pitch, and voice for different pages or sections.
• Auto-detects language based on the content.
• Fully responsive, minimal player with play/pause, volume, and download options.
• Customize player style and position (top/bottom of post, floating, etc.).
• Audio is generated using Google Cloud API, with no user-identifiable data stored.
• You can configure data processing settings to be GDPR-friendly.