glowdopera

Speechable transforms your WordPress content into natural-sounding audio using AI-powered text-to-speech technology. Speechable uses Piper TTS, an open-source neural text-to-speech engine that runs in your browser.
<h4>Third-Party Service</h4>
This plugin uses the following third-party services for text-to-speech functionality:
Piper TTS Web Library
<ul>
<li>Service Provider: <a href="https://github.com/Mintplex-Labs/piper-tts-web" rel="nofollow ugc">Mintplex Labs</a></li>
<li>Library CDN: jsDelivr (https://cdn.jsdelivr.net/npm/@mintplex-labs/piper-tts-web)</li>
<li>ONNX Runtime CDN: Cloudflare (https://cdnjs.cloudflare.com/ajax/libs/onnxruntime-web)</li>
<li>WASM Phonemizer CDN: jsDelivr (https://cdn.jsdelivr.net/npm/@diffusionstudio/piper-wasm)</li>
<li>Voice Models: Downloaded from <a href="https://huggingface.co/diffusionstudio/piper-voices" rel="nofollow ugc">Hugging Face</a></li>
<li>Terms of Service: <a href="https://github.com/Mintplex-Labs/piper-tts-web/blob/main/LICENSE" rel="nofollow ugc">MIT License</a></li>
</ul>
Whisper (Word Timestamps)
<ul>
<li>Service Provider: <a href="https://huggingface.co/docs/transformers.js" rel="nofollow ugc">Hugging Face Transformers.js</a></li>
<li>Library CDN: jsDelivr (https://cdn.jsdelivr.net/npm/@huggingface/transformers)</li>
<li>Model: Xenova/whisper-tiny.en (~75MB, downloaded on first use)</li>
<li>Purpose: Provides accurate word-level timestamps for synchronized highlighting</li>
<li>Terms of Service: <a href="https://github.com/huggingface/transformers.js/blob/main/LICENSE" rel="nofollow ugc">Apache 2.0 License</a></li>
</ul>
What data is transmitted:
<ul>
<li>The TTS library and ONNX runtime are loaded from CDN when generating audio</li>
<li>Voice model files are downloaded from Hugging Face when first using a voice</li>
<li>Whisper model is downloaded for word timestamp extraction (first use only)</li>
<li>Your content text is processed locally in your browser and is NOT sent to any external server</li>
<li>Once downloaded, all resources are cached locally in your browser</li>
</ul>
Why external resources are required:
The text-to-speech engine requires machine learning runtime (ONNX) and voice models that are too large to bundle with the plugin. These are loaded on-demand from CDN services, similar to how Google Fonts or other web services work. This is a service-based approach that keeps the plugin lightweight while providing high-quality AI voices.
<h4>Key Features</h4>
<ul>
<li>AI-Powered Voices – Natural-sounding speech using Piper TTS neural network models</li>
<li>Accurate Word Highlighting – Whisper-powered word timestamps for precise synchronization</li>
<li>12 Languages – English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian, Chinese, Japanese, Korean</li>
<li>Customizable Player – Match your theme with custom colors and styling</li>
<li>Download Audio – Let visitors download audio files for offline listening</li>
<li>Voice Presets – Quick effects like Radio, Stadium, Cave, Chipmunk, Robot, and more</li>
<li>Free – No premium version, no limits, no hidden costs</li>
</ul>
<h4>How It Works</h4>
<ol>
<li>Install and activate the plugin</li>
<li>Go to Settings → Speechable to configure your preferences</li>
<li>Edit any post and click “Generate Audio” in the sidebar</li>
<li>The audio player automatically appears on your published posts</li>
</ol>
<h4>Voice Presets</h4>
Transform your audio with one-click presets:
<ul>
<li>Default – Natural voice</li>
<li>Radio – Broadcast quality</li>
<li>Stadium – Echo effect</li>
<li>Cave – Deep reverb</li>
<li>Chipmunk – High-pitched fun</li>
<li>Deep – Low bass voice</li>
<li>Robot – Mechanical tone</li>
<li>Telephone – Phone quality</li>
<li>Megaphone – Announcement style</li>
<li>Giant – Booming voice</li>
<li>Fairy – Magical high voice</li>
<li>Narrator – Audiobook style</li>
</ul>
<h4>Perfect For</h4>
<ul>
<li>Bloggers – Give readers an audio option</li>
<li>News Sites – Accessibility for all visitors</li>
<li>Educational Content – Help students learn</li>
<li>Accessibility – Support visually impaired users</li>
<li>Podcasters – Quick audio versions of written content</li>
</ul>
<h4>Privacy</h4>
Your content is processed locally in the browser. Text is not sent to external servers. Voice models are downloaded once and cached locally.
<h3>Usage</h3>
<h4>Getting Started</h4>
<ol>
<li>After activation, go to Settings → Speechable to configure your default options</li>
<li>Select your preferred language and voice</li>
<li>Choose which post types should have audio (posts, pages, etc.)</li>
<li>Customize the player colors to match your theme</li>
</ol>
<h4>Generating Audio for a Post</h4>
Method 1: Block Editor (Single Post)
<ol>
<li>Edit any post or page in the WordPress block editor</li>
<li>Look for the “Speechable” panel in the right sidebar (under Document settings)</li>
<li>Select your preferred voice and quality settings</li>
<li>Click “Generate Audio” and wait for processing</li>
<li>Once complete, you can preview the audio before publishing</li>
<li>Publish or update your post – the audio player will appear automatically</li>
</ol>
Method 2: Posts List (Quick Access)
<ol>
<li>Go to Posts → All Posts</li>
<li>Hover over any post to see the “Audio” button in the row actions</li>
<li>Click it to open the audio generation modal</li>
<li>Configure settings and click “Generate”</li>
<li>The audio will be saved to that post</li>
</ol>
<h4>Configuring Settings</h4>
Voice Settings
<ul>
<li>Language – Choose from 12 supported languages</li>
<li>Voice – Select a voice for the chosen language (preview available)</li>
<li>Quality – Low (faster), Medium (balanced), or High (best sync accuracy)</li>
<li>Whisper Model – Controls word timestamp accuracy (Tiny is fastest, Small is more accurate)</li>
</ul>
Voice Presets
Click any preset to quickly apply pitch and reverb effects:
<ul>
<li>Default, Warm, Bright, Radio, Narrator, Podcast, Deep, Soft, Room, Hall, Telephone, Vintage</li>
</ul>
Display Settings
<ul>
<li>Post Types – Enable audio for posts, pages, or custom post types</li>
<li>Player Position – Show player before or after content</li>
<li>Word Highlighting – Enable/disable word-by-word highlighting during playback</li>
<li>Auto-scroll – Automatically scroll to keep highlighted word visible</li>
</ul>
Player Appearance
<ul>
<li>Customize background, text, button, progress bar, and highlight colors</li>
<li>Adjust border radius for rounded or square corners</li>
<li>Live preview shows your changes instantly</li>
</ul>
<h4>Managing Audio</h4>
<ul>
<li>Regenerate – Click “Regenerate” in the editor panel to create new audio with different settings</li>
<li>Delete – Remove audio from a post using the “Delete” button</li>
<li>Download – Visitors can download the audio file using the player’s download button</li>
</ul>
<h4>Tips for Best Results</h4>
<ol>
<li>Use High quality for important content where word sync matters</li>
<li>Preview voices in Settings before generating to find the best match</li>
<li>Shorter posts generate faster – consider breaking very long content into parts</li>
<li>First generation takes longer as voice models are downloaded and cached</li>
<li>Word highlighting works best with standard theme content areas</li>
</ol>
<h3>Credits</h3>
<h4>Core Technologies</h4>
<ul>
<li>
Piper TTS – <a href="https://github.com/rhasspy/piper" rel="nofollow ugc">rhasspy/piper</a> by Mike Hansen 
Fast, local neural text-to-speech system (MIT License)
</li>
<li>
Piper TTS Web – <a href="https://github.com/Mintplex-Labs/piper-tts-web" rel="nofollow ugc">Mintplex-Labs/piper-tts-web</a> v1.0.4 
Browser-compatible Piper TTS implementation (MIT License)
</li>
<li>
OpenAI Whisper – <a href="https://github.com/openai/whisper" rel="nofollow ugc">openai/whisper</a> 
Robust speech recognition for word-level timestamps (MIT License)
</li>
<li>
Transformers.js – <a href="https://github.com/huggingface/transformers.js" rel="nofollow ugc">huggingface/transformers.js</a> v3.4.1 
Run Whisper models in the browser by Xenova (Apache 2.0 License)
</li>
<li>
ONNX Runtime Web – <a href="https://github.com/microsoft/onnxruntime" rel="nofollow ugc">microsoft/onnxruntime</a> 
Machine learning inference engine (MIT License)
</li>
<li>
Piper WASM Phonemizer – <a href="https://github.com/diffusionstudio/piper-wasm" rel="nofollow ugc">diffusionstudio/piper-wasm</a> 
WebAssembly phonemizer for text processing (MIT License)
</li>
</ul>
<h4>Voice Models</h4>
<ul>
<li>
Piper Voices – <a href="https://huggingface.co/diffusionstudio/piper-voices" rel="nofollow ugc">diffusionstudio/piper-voices</a> 
High-quality neural voice models hosted on Hugging Face
</li>
<li>
Whisper Models – <a href="https://huggingface.co/Xenova" rel="nofollow ugc">Xenova on Hugging Face</a> 
Optimized Whisper models for browser inference (whisper-tiny.en, whisper-small)
</li>
</ul>
<h4>Infrastructure</h4>
<ul>
<li>jsDelivr CDN – Fast, reliable CDN for npm packages</li>
<li>Cloudflare CDN – ONNX Runtime delivery</li>
<li>Hugging Face – Model hosting and distribution</li>
</ul>
<h4>Design</h4>
<ul>
<li>Lucide Icons – <a href="https://lucide.dev" rel="nofollow ugc">lucide.dev</a> (ISC License) 
Beautiful, consistent icon set</li>
</ul>
<h4>Development</h4>
<ul>
<li>Developer: <a href="https://tanishmittal.com" rel="nofollow ugc">Tanish Mittal</a></li>
<li>Plugin Architecture: WordPress standards-compliant</li>
<li>Browser Compatibility: Modern ES6+ with Web Workers</li>
</ul>

Speechable

Convert your WordPress posts to audio with AI-powered text-to-speech. Works in the browser with word highlighting.

trinityaudio

The audio player will convert your content into audio in just a few clicks, with one-time seamless integration (no support, or special tech knowledge needed), and give your audience the ability to listen to your content on the go. 
The free version of this plugin is designed for content creators, such as bloggers who do not produce a large volume of content, and for those who want to give it a try before choosing one of the advanced plans. It enables converting up to 5 articles to audio per month, to add an audio narrator to your blog in 125 languages, 600+ voices (both male and female) and increase accessibility to broader audience.
<ul>
<li>Add rich media to your existing pages to improve SEO rankings.</li>
<li>Dashboard with statistics and usability reports.</li>
<li>Fast player loading time for a smooth experience that doesn’t affect page loading time.</li>
<li>Automatic real-time translation</li>
<li>Multiple playing speed capabilities</li>
<li>Smart Content Recommendations to enhance user engagement</li>
<li>A dedicated support team to provide assistance with any issue that might come up.</li>
</ul>
For a quick start, please follow the instructions on our <a href="https://trinityaudio.ai/the-trinity-audio-wordpress-plugin-implementation-guide/" rel="nofollow ugc">Implementation Guide</a>.
<a href="https://trinityaudio.ai/" rel="nofollow ugc">Explore</a> our advanced products and features:
<ul>
<li>Over 125 supported languages with over 600 accents and natural voices</li>
<li>CMS to manage, edit, and distribute audio content in leading platforms such as Spotify, Apple, and Google Podcast, and create playlists to increase engagement</li>
<li>Dashboard with statistics and usability reports</li>
<li>AI-powered summaries for content highlights</li>
<li>Background music integration</li>
<li>Podcast creation and distribution</li>
<li>Voice cloning technology</li>
</ul>
And much more!
<h3>Customer Testimonial</h3>
“At a time when consumption of digital audio is stronger than ever, we’re excited to roll out this new audio feature to our customers to enhance their news experience and give them the ability to listen to local journalism where and when they want it. In addition, the integration of this technology across all of our sites will drive advertising revenue.”
Jessica Gilbert, McClatchy Senior Director of Product and Experience
<h3>Trinity audio usage terms</h3>
The Trinity Audio plugin provides a Text to speech service, which is performed by Trinity Audio.
As such, the service is required to make calls to Trinity’s backend servers. 
By activating the plugin you consent to our T&C as stated below:
<a href="https://trinityaudio.ai/wp-plugin-terms/" rel="nofollow ugc">Service Terms & Conditions</a> 
<a href="https://trinityaudio.ai/privacy-policy/" rel="nofollow ugc">Privacy policy</a>
For more about Trinity Audio: <a href="https://trinityaudio.ai/" rel="nofollow ugc">Trinity Audio</a>
<h3>Settings and configurations</h3>
The following are configuration options you can modify as you see fit:
<ul>
<li>Voice Selection: Choose your content language and preferred narrator. For multilingual sites, set the primary language here and configure individual posts separately.</li>
<li>Voice Style: Select reading style (e.g., news/formal). Available for narrators with wave icons.</li>
<li>Theme & Appearance: Choose player theme and light/dark mode (or auto-adjust).</li>
<li>Audio Preview: Test your selected narrator before saving.</li>
<li>Player Features: 
** Floating Button: Control player while scrolling 
** Real-time Translation: Translate content to 6 languages in real-time 
** Author Credit: Include author name in audio 
** Playback Speed: Set default speed (users can adjust during playback). 
** Share: Allow users to share the audio with friends, social media or yourself to listen later</li>
<li>Content Filtering: 
** Skip HTML Tags: Exclude specific HTML elements from audio 
** Allow Shortcodes: Include shortcode content (comma-separated: vc_row, vc_column, su_heading)</li>
<li>Player Settings: 
** Position: Choose player placement (recommended: before article text) 
** Label: Add custom text above player (HTML supported) 
** Trinity Credit: Display “Powered by Trinity Audio” attribution 
** Performance: Enable resource preconnect for faster loading 
** Auto-Enable: Automatically add player to new posts</li>
</ul>
Still here? Go turn your readers to listeners.
<h3>Video</h3>
<iframe loading="lazy" class="youtube-player" width="750" height="422" src="https://www.youtube.com/embed/3D5-xPLA_QA?version=3&rel=1&showsearch=0&showinfo=1&iv_load_policy=1&fs=1&hl=en-US&autohide=2&wmode=transparent" allowfullscreen="true" style="border:0;" sandbox="allow-scripts allow-same-origin allow-popups allow-presentation allow-popups-to-escape-sandbox"></iframe>

Trinity Audio – Text to Speech AI audio player to convert content into audio

Test


The support was fast and the plugin works great


Fast support, works great

The audio player will convert your content into audio in just a few clicks, with one-time seamless integration (no support, or special tech knowledge  …

Speechable vs Trinity Audio – Text to Speech AI audio player to convert content into audio