The Talker Text-to-Speech WordPress Plugin powered by Microsoft Azure is a tool that utilizes advanced machine learning and artificial intelligence to convert website content into natural-sounding human speech. This innovative plugin ensures fast and dependable performance worldwide. With over 450 voices available in 75+ languages and variants, the Talker Plugin uses cutting-edge speech synthesis techniques, including Neural, to produce high-quality audio output.
One of the key features of the Talker Plugin is its support for the Speech Synthesis Markup Language (SSML) standard. This allows users to customize the speech output for each page or article on their website, including the ability to pause, add intonation, and read out numbers and phone numbers in a human-like format. Additionally, the SSML feature of the Talker Plugin enables multiple voices and languages to be used within a single article, making it a valuable tool for online language courses or articles that feature interviews.
The product is fully compatible with the most popular WordPress editors. With the flexible plugin settings, you can enable/disable it on different pages, for different user groups, on different devices(mobile, tablet, desktop).
The Talker plugin comes with built-in widgets for Elementor and WPBakery builders. Widgets are used to add a player with generated audio to your website pages.
Batch processing is used to convert into speech all selected pages or posts on your site. For this, just make a few clicks on the familiar WordPress interface and the audio files are generated for all your posts regardless of their number.
Supports a customizable into and outro text that will be added when synthesizing audio files. It is a useful feature if you want to brand all your files 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 are used to manage the player display positions as well as its appearance in accordance with your needs and wishes. Also, 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.
Custom post types support. If your theme uses custom post types or you have installed them separately, there are no problems for Talker to voice them as the regular WordPress posts or pages.
The link to download option allows you to get the generated audio file from both the Front-end and the Back-end.
With the plugin, you can also construct an RSS feed for publishing on the largest podcasting services, such as Apple Podcasts, Google Podcasts, Spotify, and more.
The Talker is fullycross-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, Restaurant or Retail Company.
Please note, for the correct plugin works you need authorization from a valid Microsoft Azure Account.
Learn a little more about what the plugin can do and how to configure it from the Online Documentation.
1.0.10 - 24 May 2024 Added talker-lang shortcode for adjusting the speaking language in multilingual voices
1.0.9 – 3 May 2024 Fixed generating audio with multilingual voices
1.0.8 – 13 March 2024 Added automatic synthesis setting Added removing audio file data from post meta on audio delete from post
1.0.7 – 8 February 2023 Added inner request verification for get page content
1.0.6 – 14 December 2023 Fixed slow loading for the posts list page by using Microsoft Azure Storage
1.0.5 – 8 December 2023 Fixed styles on WPBakery edit page
1.0.4 – 14 November 2023 Added Speech Templates
1.0.3 – 4 October 2023 Added saving audio file to Microsoft Azure Blob storage Added talker-lexicon shortcode for custom lexicon Added ability to use custom lexicon globally for all posts
1.0.2 – 4 July 2023 Added output format setting Fixed generating audios with bulk actions Fixed volume range in advanced voice settings
1.0.1 – 19 May 2023 Fixed generating audio based on big text
1.0.0 – 13 May 2023 Initial release