AI Auto Alt Text Generator
AI Auto Alt Text Generator is a lightweight, privacy-conscious plugin that uses OpenAI vision-capable models (defaulting to GPT-5.4 nano, with GPT-5.4 mini and legacy GPT-4o mini options) to create meaningful, screen-reader-friendly alt text and SEO-friendly titles for your images. Whether you add a single image, bulk-process your library, or just want a one-click fix in the Media Library, the plugin handles it all – no manual effort required. This solution is far cheaper than many alternatives because it cuts out the middle-person. You’ll just need to bring your own OpenAI API key. ✨ Key features Automatic alt text on upload – set-and-forget accessibility. Optional automatic image titles – improve SEO with descriptive titles. One-click manual generation – “Generate Alt Text & Title” button in the Media Library. Bulk update tool – batch-process existing images, including those that only have filename-based alt text, with a configurable pause between batches. Prompt fine-tuning – supply site-wide context and optionally include the image file name. Model selection – default to GPT-5.4 nano (fastest & cheapest) or switch to GPT-5.4 mini for higher quality; legacy GPT-4o mini and GPT-5 mini/nano remain available. Image size & detail control – choose the resolution and level of visual detail sent. Developer-friendly – filters and actions to customise prompts, models and output, plus optional outgoing webhooks. WordPress Abilities API – registers a generate-alt-text ability (WordPress 6.9+/7.0) so core AI, agents and automation tools can generate alt text. No extra servers – data flows only between your site and OpenAI; nothing is stored off-site. Multilingual output – choose English (UK), English (US) or other popular languages. (English US is the default.) 🧭 Where to find the bulk tool Tools → Bulk Alt Text Update Media → Bulk Alt Text Update (shortcut that redirects to the Tools page) Settings → Alt Text Generator includes a button linking straight to the bulk page 🧠 How it works When an image is uploaded (or manually chosen), the plugin creates a temporary public URL for that image. It sends the image – plus optional context such as the parent post title, your custom site context and the file name – to your selected OpenAI vision model. OpenAI returns a concise description. Alt text is stored in WordPress’ native _wp_attachment_image_alt field. (Optional) The returned title is stored as the attachment post title. Nothing is cached or stored on OpenAI’s side; only the final strings live in your database. Settings overview OpenAI API Key – Required to connect to OpenAI. OpenAI Model – GPT-5.4 nano (default), GPT-5.4 mini, or legacy GPT-4o mini / GPT-5 mini / GPT-5 nano. Image Size to Send – Thumbnail, Medium, Large, or Full. Image Detail Quality – ‘Low’ or ‘High’ (Low uses fewer tokens). Bulk batch size – Number of images per batch (lower values reduce rate-limit risk). Site Context – Optional free-form prompt guidance (brand voice, niche, etc.). Send Image File Name – Include file name in the prompt for extra context. Automatically Generate Title – Add descriptive titles alongside alt text. Use full context for image titles – When enabled, title generation includes site context and file name (uses more tokens). Bulk optimiser delay (seconds) – Pause between batches during bulk runs. OpenAI request timeout (seconds) – Max wait time for OpenAI responses (10–120s) to reduce timeout failures on slower hosts. Output Language – Default English (US). Choose English (UK) for British spellings or another popular language; outputs (alt text and titles) will be generated in the selected language. Webhook URL & signing secret – Optionally POST generated alt text/titles to an external endpoint (with an optional HMAC-SHA256 signature) for automation and logging. Developers The plugin is extensible via standard WordPress hooks, an outgoing webhook, and the WordPress Abilities API. Filters aatg_alt_text_prompt ( $prompt, $post_ID, $context ) – customise the alt-text prompt. aatg_image_title_prompt ( $prompt, $post_ID, $context ) – customise the title prompt. aatg_openai_request_payload ( $payload, $context, $messages ) – customise the full OpenAI request (model, messages, reasoning effort). aatg_generated_alt_text ( $alt_text, $post_ID ) – filter alt text before it is saved. aatg_generated_title ( $title, $post_ID ) – filter the title before it is saved. aatg_is_low_quality_alt ( $is_low, $alt, $post_ID ) – control which existing alt text the bulk tool regenerates. aatg_webhook_payload ( $payload, $post_ID, $result ) – customise the outgoing webhook body. aatg_supported_image_extensions ( $extensions ) – customise which image formats are sent to OpenAI (default: PNG, JPEG, GIF, WebP). Actions aatg_after_alt_text_generated ( $post_ID, $alt_text ) aatg_after_title_generated ( $post_ID, $title ) aatg_after_generation ( $post_ID, $result ) Outgoing webhook Set a Webhook URL under Settings → Integrations & Webhooks to receive a non-blocking JSON POST after each generation. If a signing secret is set, requests include an X-AATG-Signature: sha256=… header (HMAC-SHA256 of the body) so your endpoint can verify authenticity. WordPress Abilities API On WordPress 6.9+ the plugin registers the ability ai-auto-alt-text/generate-alt-text (input: attachment_id) so WordPress core AI, agents, MCP servers and automation tools can generate alt text programmatically. Execute it with wp_get_ability( 'ai-auto-alt-text/generate-alt-text' )->execute( array( 'attachment_id' => 123 ) ). External services This plugin connects to the OpenAI API to generate alt text and (optionally) image titles. Endpoint: https://api.openai.com/v1/chat/completions When called: On image upload (automatic) Via “Generate Alt Text & Title” button in Media Library (manual) Via Tools → Bulk Alt Text Update (bulk) Data sent: image URL, optional file name, optional site context, optional parent post title Terms: https://openai.com/policies/terms-of-use Privacy: https://openai.com/policies/privacy-policy If you configure a Webhook URL, generated alt text/titles (and the image URL) are also sent to that endpoint you control.
GSpeech TTS – WordPress Text To Speech Plugin
Text to Speech WordPress Plugin – GSpeech TTS GSpeech is an advanced WordPress Text to Speech plugin that converts WordPress posts, pages, and WooCommerce product descriptions into natural-sounding text-to-audio narration in 98 languages. It automatically adds a modern WordPress audio player to your website, allowing visitors to listen to articles, blog posts, and product content instead of just reading them. GSpeech works as a lightweight WordPress text-to-speech bridge between your website and the GSpeech Cloud. Instead of generating audio on your WordPress server, GSpeech handles voice synthesis, audio storage, smart caching, and playback delivery in the cloud, helping your site stay fast while visitors listen to your content. 🔗 WordPress Text to Speech Plugin Setup & Useful Links Live Demo | Setup Guide | Reviews | Support | Dashboard | Pricing | Videos | Blog ⚡ Add Text to Speech to WordPress in Minutes GSpeech combines simple setup with a powerful cloud audio platform built for publishers, businesses, and content creators. ✅ Add Text to Speech to Your Website – Convert WordPress posts, pages, WooCommerce content, and selected text into natural-sounding audio. ✅ Unified AI Voice Engine (commercial plans) – Access 300+ voices in 98 languages powered by Google Cloud Text-to-Speech, OpenAI, Gemini, Chirp3 HD, Neural2, Polyglot, and WaveNet through one GSpeech platform, without managing separate provider accounts or API keys. ✅ GSpeech Cloud Console – Manage multiple websites, voices, audio players, translations, analytics, and generated audio files from one unified cloud dashboard. ✅ Real-Time Audio Translation (commercial plans) – Translate website content and selected text into listenable audio using any GSpeech player, including Read Highlighted Text, even on single-language websites. ✅ Multiple Customizable Audio Players – Choose from Full Page, Button, Circle, Floating, Context, and Read Highlighted Text (RHT) players for different layouts and listening experiences. ✅ First-Listen Cloud Generation – Audio is generated in the GSpeech Cloud when a visitor first requests playback, then securely stored and intelligently cached for future plays without repeated synthesis or additional WordPress server load. ✅ Back-Catalog Cloud Generation – Posts from past years generate on first listen. You do not pre-generate the entire archive or spend characters on unread old articles. ✅ Secure Cloud Storage – Generate Once, Keep and Play – Audio is generated once and securely stored in the GSpeech Cloud. Previously generated files are not deleted when your plan changes and remain available in your dashboard for playback and download. ✅ One-Click Activation – Activate the GSpeech Cloud Console from WordPress Admin and start generating audio in minutes. ✅ Cloud Processing, No Server Load – Voice synthesis, audio storage, smart caching, and playback delivery are handled in the GSpeech Cloud, keeping your WordPress hosting fast and lightweight. ✅ No API Keys Required – Use cloud text-to-speech voices without managing Google, OpenAI, Gemini, or other external API accounts. ✅ Smart Audio Sync – Updated WordPress content automatically regenerates audio so visitors always hear the latest version. ✅ Intelligent Content Isolation – Target the real article content and exclude menus, sidebars, ads, footers, URLs, shortcodes, and other unwanted elements from audio playback using flexible content rules. ✅ Multilingual Audio (commercial plans) – Automatically adapt audio to the active website language and let visitors listen in 98 languages, making GSpeech ideal for multilingual WordPress websites. ✅ Voice Prompts & Emotions (commercial plans) – Use custom prompts, voice instructions, emotions, and styles to control narration tone, delivery, and brand voice. Trusted by thousands of websites, GSpeech processes over 200 million characters per month, is rated ⭐4.8/5 on WordPress.org, and has 220+ five-star reviews across WordPress.org, Joomla, AppSumo, and Trustpilot. Since 2012, GSpeech has pioneered WordPress text-to-speech innovations now widely adopted across the industry, starting with Listen to Selected Text, which evolved into today’s Read Highlighted Text (RHT) Player. In 2023, GSpeech was the first WordPress text-to-speech platform to introduce First-Listen Cloud Generation with the GSpeech Cloud Console. Unread articles do not consume generation characters. Similar first-listen patterns have since become common. Unlike many text-to-speech plugins that rely on limited browser voices or require users to configure and pay for external API keys, GSpeech provides a cloud-powered WordPress text-to-speech platform with simple setup, all-in-one pricing, and no API key management. Audio is generated using advanced cloud voices, optimized through the GSpeech cloud infrastructure, and cached for fast playback across browsers and devices. GSpeech can also generate audio for very long articles, supporting content with up to 7 hours of playback per article. Commercial plans include ultra-realistic AI voices powered by OpenAI, Google Cloud Text-to-Speech, and Gemini AI voice models, including OpenAI TTS, Gemini Flash TTS, Gemini Pro TTS, Chirp3 HD, Neural2, Polyglot, and WaveNet. Users can adjust speed and pitch, use custom voice prompts, add voice instructions, and control narration style with the unique Voice Vibes system with 100+ expressive voice styles, including emotional, warm, confident, calm, whisper, narrator, and branded voice directions. The integrated GSpeech Cloud Console lets users generate and manage WordPress text-to-speech audio directly from the admin panel. Commercial plans also support real-time audio translation in 98 languages, helping websites become multilingual audio experiences. The same GSpeech engine can also be integrated into Shopify, Wix, Joomla, and custom HTML websites, enabling publishers to add text-to-speech audio across multiple platforms. 🎬 WordPress Text-to-Speech Plugin – Step-by-Step Video Tutorial 🎬 GSpeech – Full Text-to-Speech Platform Overview 👆 Why Use the GSpeech Text-to-Speech Plugin? ✅ Improve Website Accessibility – Provide audio versions of your content for visitors who prefer listening instead of reading. ✅ Increase Engagement – Let users listen to articles, blog posts, and product descriptions while browsing or multitasking. ✅ Boost SEO and Time on Page – Audio content can improve engagement signals and create a richer user experience. ✅ Repurpose Written Content – Turn posts, pages, tutorials, and WooCommerce descriptions into reusable audio experiences. 🎯 Use Cases – Where WordPress Text-to-Speech Is Most Valuable GSpeech helps different types of websites turn written content into engaging audio experiences. 📰 Blogs and News Websites – Let readers listen to long articles and narrated blog posts while multitasking, commuting, or working. 🛒 WooCommerce Product Pages – Add audio narration to product descriptions to improve accessibility and engagement. 🎓 Education and E-Learning – Help students absorb lessons and documentation through audio learning. 📚 Long-Form Articles and Documentation – Make guides, tutorials, and reports easier to consume through text-to-speech narration. 🌍 Multilingual Websites – Reach global visitors with multilingual audio in 98 languages. 👉 Text to Speech by GSpeech – Core Plugin Features ✅ Easy Setup & One-Click Activation: Activate the GSpeech Cloud Console from WP Admin and add audio to posts, pages, custom post types, and WooCommerce content without server configuration. ✅ 98 Languages & Cloud Voices: Generate natural-sounding speech through GSpeech-managed cloud engines. Voice and language availability varies by plan (Free and Personal machine: 68 languages; commercial Unified AI Voice Engine: 300+ voices in 98 languages), with no external API keys required. ✅ Cloud Processing, Smart Caching & Sync: Voice generation, storage, and delivery run in the GSpeech Cloud, keeping WordPress fast and lightweight. Audio is generated once, played unlimited times, and automatically regenerated when content changes. ✅ Multiple Audio Players: Use Full Page, Button, Circle, Floating, Context, and Read Highlighted Text (RHT) players for different layouts and listening experiences. ✅ Read Highlighted Text (RHT): The modern evolution of GSpeech’s original Listen to Selected Text feature, introduced in 2012. Visitors can select any passage and listen instantly – Demo. ✅ Shortcodes & Display Rules: Insert players with [gspeech], [gspeech-button], or [gspeech-circle] and control where they appear across your website. ✅ Long-Article Support: Generate audio for content with up to 7 hours of playback per article. ✅ Intelligent Content Isolation: Exclude menus, ads, sidebars, footers, URLs, shortcodes, special characters, and other unwanted elements from audio output. ✅ Smart Pronunciation Aliases: Customize how brand names, acronyms, technical terms, and names are spoken using global, language-based, or locale-specific pronunciation rules, while keeping the visible website text unchanged. Learn more. ✅ Audio Database & Analytics: Administrators can manage and download generated audio files, and track plays by country, city, and device directly from WP Admin. ✅ Welcome Messages: Greet visitors with automatic audio and control where and how often messages play. ✅ Customizable Responsive Players: Choose from 16+ themes with modern, mobile-friendly, and cross-browser-compatible designs. ✅ Professional Support: Get fast and friendly help from the GSpeech team. ⚙️ WordPress Compatibility GSpeech works seamlessly with most WordPress environments, including popular themes, page builders, multilingual plugins, caching systems, and WooCommerce websites. ✅ Gutenberg Editor ✅ WooCommerce ✅ Divi ✅ Elementor ✅ WPBakery ✅ GTranslate, WPML, Polylang, TranslatePress ✅ WP Rocket, LiteSpeed Cache, W3 Total Cache ✅ Yoast SEO, RankMath, All in One SEO The plugin works with most WordPress themes and hosting environments without requiring special server configuration. 🌍 Supported Languages – WordPress Text to Speech in 98 Languages GSpeech supports 98 languages for text-to-speech generation, making it ideal for multilingual WordPress websites and global audiences. Free and Personal machine plans include 68 languages. Personal 100K AI and above include 98 languages. Some of the most popular supported languages include: English (US, UK, AU) (English): Text to Speech Spanish (Spain, US, Latin America, Mexico) (Español): Texto a voz French (France, Canada) (Français): Synthèse vocale German (Deutsch): Text-zu-Sprache Italian (Italiano): Sintesi vocale Portuguese (Brazil, Portugal) (Português): Texto para fala Russian (Русский): Преобразование текста в речь Armenian (Հայերեն): Տեքստից խոսք Arabic (العربية): تحويل النص إلى كلام Hebrew (עברית): טקסט לדיבור Hindi (हिन्दी): पाठ से वाक् Bengali (বাংলা): টেক্সট টু স্পিচ Chinese (中文): 文字转语音 Japanese (日本語): テキスト読み上げ Korean (한국어): 텍스트 음声 변환 Additional supported languages include Afrikaans, Albanian, Amharic, Basque, Bosnian, Bulgarian, Catalan, Cantonese, Croatian, Czech, Danish, Estonian, Filipino, Finnish, Galician, Greek, Gujarati, Georgian, Hungarian, Icelandic, Indonesian, Javanese, Kannada, Kazakh, Khmer, Latin, Latvian, Lithuanian, Luxembourgish, Lao, Macedonian, Malay, Malayalam, Marathi, Maori, Mongolian, Nepali, Norwegian, Persian, Punjabi, Romanian, Serbian, Sinhala, Slovak, Slovenian, Swedish, Swahili, Tamil, Telugu, Thai, Urdu, Welsh, and more. See the full list of supported languages in the FAQ section. 📚 Usage and Shortcodes ✅ Activate the GSpeech Cloud Console directly from WP Admin with one click. ✅ The audio player can automatically appear on posts, pages, and WooCommerce products. ✅ Manage player settings in Cloud Console → Widgets. ✅ Use shortcodes: [gspeech], [gspeech-button], and [gspeech-circle]. ✅ The Read Highlighted Text (RHT) player works automatically after activation. ✅ Exclude elements from audio playback using the class nospeech. ✅ View player examples on the Demo Page. 🛟 Support For free plugin questions, please use the WordPress.org support forum. For GSpeech account, billing, Cloud Console, commercial features, or website-specific setup, please contact GSpeech Support. 💬 WordPress Text to Speech Plugin – CUSTOMER TESTIMONIAL A Premium Text-to-Speech Service ⭐⭐⭐⭐⭐ Unite.AI praised GSpeech for natural voice quality, accessibility, and stronger user engagement on long-form AI content. — Antoine Tardif – CEO Unite.AI ⭐ What Users Say About GSpeech Read real feedback from publishers, bloggers, and website owners on the GSpeech Testimonials page. 🚀 Upgrade to GSpeech Commercial Plans for Advanced Features Unlock premium features by upgrading to GSpeech Commercial. The commercial version of the plugin provides advanced capabilities, premium AI voices, and the best listening experience for your visitors. 🌟 GSpeech Text-to-Speech – Commercial Features ✅ Unified AI Voice Engine: Access 300+ voices in 98 languages through one GSpeech platform. Choose from premium AI voices powered by OpenAI, Google Cloud Text-to-Speech, Gemini AI voice models, Chirp3 HD, Neural2, Polyglot, and WaveNet without managing separate provider accounts or API keys. Control speed, pitch, and voice style to match your content. See demo (AI voices marked with a star). ✅ Real-Time Audio Translation: Translate website content instantly into supported languages and let visitors listen using any GSpeech player, including selected text with the Read Highlighted Text feature. See the language list in the FAQ. ✅ Multilingual Mode: Automatically detects the active website language and generates speech with the appropriate voice. Perfect for multilingual WordPress websites using GTranslate, WPML, Polylang or TranslatePress. ✅ Custom Voice Prompts, Instructions and Emotions: Use custom prompts, voice instructions, expressive styles, and emotional delivery to control tone, mood, narration style, and brand voice. ✅ Voice Vibes: Choose from 100+ expressive voice styles, including emotional, warm, confident, calm, whisper, narrator, and branded voice directions. ✅ Voice Tuning: Adjust speaking pitch (±20 semitones) and speed (up to 4× faster or slower). ✅ Smart Pronunciation Aliases: Language- and locale-based spoken replacements for brands, acronyms, and names. Visible copy stays unchanged. Learn more. ✅ Advanced Player Features: Includes real-time captions, a sticky context player, voice selection, and real-time audio translation directly from the player. ✅ GTranslate Compatibility: Works seamlessly with the GTranslate multilingual plugin. ✅ Simple Pricing, No API Keys Required: Access premium OpenAI, Google Cloud, and Gemini AI voices with one straightforward GSpeech plan. No separate API accounts, usage tracking, or external billing required. ✅ RHT Advanced Views: Access RHT Player View 2 and View 3 with translation and text panels. See demo. ✅ Download Audio: Allow visitors to download audio files (.mp3) directly from the player. ✅ Seamless Updates: Cloud-based SaaS architecture – no manual updates required. 👉 Web Content Accessibility (WCAG) Guideline Text-to-Speech by GSpeech helps WordPress websites improve accessibility and support WCAG standards with just one click. 🎬 GSpeech Text to Speech – WordPress Video Tour 🎬 Text to Speech for WordPress – Transform Text into Audio with AI Voices 🎬 Why GSpeech Lifetime Deal Is a Powerful WordPress Text-to-Speech Solution 🌟 Expert Reviews & Featured Mentions GSpeech is recommended by technology reviewers and listed among the best WordPress text-to-speech plugins. Top 10 Text-to-Speech Plugins for WordPress – Unite AI GSpeech Review – Techozens Best Text-to-Speech Plugins for WordPress – BDThemes 7 Best Text-to-Speech WordPress Plugins – WPExplorer ⚙️ GSpeech Text to Speech (3.X) Usage Terms GSpeech 3.X is powered by the GSpeech cloud backend. By using it, you agree to the Terms of Service. GSpeech also includes legacy GSpeech 2.X mode. GSpeech 2.X legacy features: ✅ Unlimited text-to-speech conversions ✅ Place speakers anywhere using {gspeech}text to speech{/gspeech} 🔗 Live Demo 🔗 Documentation