Speaker is a WordPress Plugin designed to converts website page content into human-like speech. The plugin uses the latest technology of machine learning and artificial intelligence to play a high-quality human voice and add an audio player with content to the page. The Speaker plugin basis is the Google Cloud Platform, which ensures the plugin’s reliability and speeds anywhere in the world.
The Speaker WordPress Plugin converts text into human-like speech in more than 340 voices across 52+ languages and variants. It applies groundbreaking research in speech synthesis (WaveNet and Neural2) and Google’s robust neural networks to deliver high-fidelity audio.
The Speaker is the only WordPress Plugin that supports the Speech Synthesis Markup Language(SSML) standard. SSML allows you to fine-tune speech for each article on your website. You can pause, intonate, read numbers, and telephones in the usual format for humans. Besides, the SSML in the Speaker allows using several voices and languages in a single article. For example, you can voice an article with an interview in several different voices or use this feature for online language courses.
This product has been tested and is fully compatible with all popular WordPress editors. Incredibly flexible plugin settings allow you to enable/disable it on different pages, for different user groups, on different devices(mobile, tablet, desktop).
A lot of useful functions and settings
In the Speaker, you can create custom Speech Templates for each page. Also, for each post in WordPress, a custom Speech Template can be created and used.
Batch processing allows you to convert into speech all the existing pages of your site. To do this, just make a few clicks on the familiar WordPress interface. It doesn’t matter how many posts on your site are 5 or 5,000 for all of its speech will be synthesized and an audio file generated.
Customizable intro and outro for all synthesized speech files, a very convenient feature if you want all your files to be branded in the same style. For example, you can add a greeting or copyright at the beginning and/or end of each speech file.
Flexible design features allow you to customize the player’s appearance to your liking and place it in different positions on the page. Besides, you can place several players on one page. For example, if you want to insert audio versions of several other articles into one article to maintain the story’s context.
The Speaker is GDPR-compliant, which means it can’t use or send private or not public page content.
The audio of a post/page is generated based on the current page markup available publicly. If you use password-protected post types available only for specific users or a group of users, the Speaker can’t work with them.
Many of the customers requested a link to download the audio file. And we did it for you! With just one setting, you can enable displaying the download link on both the Front-end and the Back-end.
With the Speaker, you can not only create an audio version of your text entries, but also construct an RSS feed for publishing on the largest podcasting services, such as Apple Podcasts, Google Podcasts, Spotify, and more.
We continuously monitor the latest innovations and trends in the development universe. And they prepared a plugin to work with the newest version of PHP. However, you can use the plugin on older versions as well. The speaker is compatible with the PHP version starting from 5.6 and up to the most recent stable versions.
The new user interface has been made specifically for version 2.0. The UI is inspired by the Material Design style and looks fresh and modern.
Speaker is fully cross-browser. It does not matter which browser users view your site. Chrome, Firefox, Opera, Safari, Edge, or even the outdated versions of Internet Explorer – visitors will get an incredible experience in all browsers. Moreover, this is especially important if your site has many long pages, such as a Blog, Portfolio, Corporate Website, eCommerce Project, Creative Agency, Real Estate Listing, Personal CV, a Restaurant or Retail Company.
Features of the Text-to-Speech Plugin
- Visual Speech Template Builder
- Supported SSML for WordPress
- Batch processing WordPress Pages and Posts
- Automatically synthesizing audio after saving the page
- Multiple voices and languages on the single page
- Custom pauses and intonation
- Fully supported of Custom WordPress Post Formats
- 52+ Languages Includes
- More than 340 human-like voices
- WaveNet and Neural2 voices included
- Customizable speech speed and pitch for each voice
- Custom audio Intro and Outro
- Automatic backup audio files to the Google Drive
- RSS Podcasts feed for Google Podcasts and Apple Podcasts
- Includes addon for Elementor & widget for WPBakery
- Tested and compatible with Elementor, WPBakery Page Builder and Visual Composer
- Speakable Markup for search engines
- Works well with all popular WordPress Themes
- Gutenberg Ready
- Five Player Styles
- Download link on Front-end and(or) Back-end
- Seven Positions for Placing the Player
- Includes Player Shortcode to Place Anywhere on the Website
- Perfect for RTL direction
- Beautiful modern User Interface
- Tested and Compatible up to WordPress 6+
- Lightweight and Fast
- Powered by Google Cloud Platform
- Compatible with all Modern Browsers
- Includes exclusive access to WaveNet technology
- Easy to use and customize
- Installation Guide
- Detailed Users Manual
- Huge Customization Capabilities
- Six months Included Support for CodeCanyon buyers
Speaker Text-to-Speech Plugin tested and compatible with All Major WP Plugins: Yoast SEO, Contact Form 7, W3 Total Cache, NextGen Gallery, Slider Revolution, WooCommerce, etc. It also works perfectly and improves the user experience with popular Website Page Builders, like Elementor, Visual Composer, Gutenberg, Beaver Builder, Divi, Themify Builder, WP Bakery Page Builder, Layers WP, and many others. The plugin works perfectly with all significant WordPress frameworks: Genesis, Divi, Themify, Warp 7, Ultimatum, Beans, Unyson, Gantry, and others.
Learn a little more about what the plugin can do and how to configure it from the Online Documentation.
Please note, for the correct plugin works you need authorization by valid Google Account.
3.4.3 - 21 January 2023 Fixed duplicated voices for some languages Fixed backend UI scripts initialization for some customer cases Fixed escaping third-party plugins returns statements Fixed styles for non Gutenberg page edit interface Decrease minimum supported PHP version from 7.4 to 7.2.5
3.4.2 - 28 December 2022 Added 14 News voices for English languages Improved accessibility of the default browser player
3.4.1 - 12 October 2022 Added Audio Encoding option, Sample rate option and Volume option
3.4.0 - 4 October 2022 Added Neural2 voices for English languages Added text description before/after the audio player block Added the Speakable Markup JSON+LD snippet Added RSS feed for Google Podcasts and Apple Podcasts Added speaker-say-as, speaker-prosody, speaker-sub, speaker-emphasis and speaker-voice HTML attributes to extend SSML functionality Added the ability to make substitutions in audio content using regular expressions Added dashboard widget to show used free quota Added Audio Content settings tab, Speakable Markup settings tab and Podcasts settings tab Before Audio Text, After Audio Text, Read the Title and Read the Image Caption options moved to the Audio Content Tab
3.3.10 - 3 September 2022 Added Marathi (India) language and 6 voices
More changes in the changelog