{"id":308029,"date":"2026-05-02T15:21:09","date_gmt":"2026-05-02T15:21:09","guid":{"rendered":"https:\/\/wordpress.org\/plugins\/antradus-ai-lite\/"},"modified":"2026-09-09T21:11:52","modified_gmt":"2026-09-09T21:11:52","slug":"antradus-ai-lite","status":"publish","type":"plugin","link":"https:\/\/fy.wordpress.org\/plugins\/antradus-ai-lite\/","author":20459625,"comment_status":"closed","ping_status":"closed","template":"","meta":{"version":"2.10.0","stable_tag":"2.10.0","tested":"7.1.1","requires":"5.8","requires_php":"7.4","requires_plugins":null,"header_name":"Antradus AI \u2014 AI SEO Content, Bulk Posts & Image Creator","header_author":"ehabahmad","header_description":"AI-powered article and image generator. Write SEO-optimized content from a keyword or URL using OpenAI, Claude, Gemini, or OpenRouter. Works in both Classic and Block editors.","assets_banners_color":"6e868c","last_updated":"2026-09-09 21:11:52","external_support_url":"","external_repository_url":"","donate_link":"","header_plugin_uri":"https:\/\/antradusai.com\/","header_author_uri":"","rating":5,"author_block_rating":0,"active_installs":0,"downloads":1434,"num_ratings":1,"support_threads":0,"support_threads_resolved":0,"author_block_count":0,"sections":["description","installation","faq","changelog"],"tags":{"1.0.0":{"tag":"1.0.0","author":"ehabahmad","date":"2026-05-02 17:04:18","revision":3521038},"1.0.1":{"tag":"1.0.1","author":"ehabahmad","date":"2026-06-13 17:11:21","revision":3571211},"2.0.1":{"tag":"2.0.1","author":"ehabahmad","date":"2026-07-24 22:47:55","revision":3621994},"2.10.0":{"tag":"2.10.0","author":"ehabahmad","date":"2026-09-09 21:11:52","revision":3689010}},"upgrade_notice":[],"ratings":{"1":0,"2":0,"3":0,"4":0,"5":1},"assets_icons":{"icon-256x256.png":{"filename":"icon-256x256.png","revision":3520992,"resolution":"256x256","location":"assets","locale":"","width":256,"height":256}},"assets_banners":{"banner-1544x500.png":{"filename":"banner-1544x500.png","revision":3524706,"resolution":"1544x500","location":"assets","locale":"","width":1544,"height":500},"banner-772x250.png":{"filename":"banner-772x250.png","revision":3524728,"resolution":"772x250","location":"assets","locale":"","width":772,"height":250}},"assets_blueprints":{},"all_blocks":[],"tagged_versions":["1.0.0","1.0.1","2.0.1","2.10.0"],"block_files":[],"assets_screenshots":{"screenshot-1.png":{"filename":"screenshot-1.png","revision":3520998,"resolution":"1","location":"assets","locale":"","width":1200,"height":900},"screenshot-2.png":{"filename":"screenshot-2.png","revision":3520999,"resolution":"2","location":"assets","locale":"","width":1200,"height":900},"screenshot-3.png":{"filename":"screenshot-3.png","revision":3521000,"resolution":"3","location":"assets","locale":"","width":1200,"height":900},"screenshot-4.png":{"filename":"screenshot-4.png","revision":3521002,"resolution":"4","location":"assets","locale":"","width":1200,"height":900},"screenshot-5.png":{"filename":"screenshot-5.png","revision":3521060,"resolution":"5","location":"assets","locale":"","width":1200,"height":900},"screenshot-6.png":{"filename":"screenshot-6.png","revision":3521024,"resolution":"6","location":"assets","locale":"","width":1200,"height":900}},"screenshots":{"1":"Choose your model (OpenRouter supports free models)","2":"Antradus AI main view","3":"Antradus AI rewrite from external source","4":"Antradus AI writing and style features","5":"Antradus AI Image capabilities","6":"Antradus AI find your settings page"}},"plugin_section":[],"plugin_tags":[2353,13175,25198,194533,186],"plugin_category":[55],"plugin_contributors":[261665],"plugin_business_model":[],"class_list":["post-308029","plugin","type-plugin","status-publish","hentry","plugin_tags-ai","plugin_tags-content-generator","plugin_tags-image-generation","plugin_tags-openai","plugin_tags-seo","plugin_category-seo-and-marketing","plugin_contributors-ehabahmad","plugin_committers-ehabahmad"],"banners":{"banner":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/banner-772x250.png?rev=3524728","banner_2x":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/banner-1544x500.png?rev=3524706","banner_rtl":false,"banner_2x_rtl":false},"icons":{"svg":false,"icon":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/icon-256x256.png?rev=3520992","icon_2x":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/icon-256x256.png?rev=3520992","generated":false},"screenshots":[{"src":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/screenshot-1.png?rev=3520998","caption":"Choose your model (OpenRouter supports free models)"},{"src":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/screenshot-2.png?rev=3520999","caption":"Antradus AI main view"},{"src":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/screenshot-3.png?rev=3521000","caption":"Antradus AI rewrite from external source"},{"src":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/screenshot-4.png?rev=3521002","caption":"Antradus AI writing and style features"},{"src":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/screenshot-5.png?rev=3521060","caption":"Antradus AI Image capabilities"},{"src":"https:\/\/ps.w.org\/antradus-ai-lite\/assets\/screenshot-6.png?rev=3521024","caption":"Antradus AI find your settings page"}],"raw_content":"<!--section=description-->\n<p><strong>Antradus AI Lite<\/strong> writes complete, SEO-optimized articles with a matching AI featured image \u2014 right inside the WordPress post editor, using your own AI provider key. No middleman, no per-word fees: bring your OpenAI, Anthropic (Claude), Google Gemini, OpenRouter, or DeepSeek key and start writing.<\/p>\n\n<p>Describe your topic, pick a writing style and tone, and the plugin writes a full article plus the focus keyword, SEO meta title, and meta description \u2014 shown with one-click Copy buttons so you can paste them into your SEO plugin. Paste any external link and rewrite that article in your own voice. Highlight any sentence while editing and let the AI rewrite, improve, expand, shorten, fix, or translate it. Then generate a matching featured image with one click.<\/p>\n\n<p>Every article it writes carries a short AI disclosure at the bottom, naming the model that wrote it \u2014 on by default, in your own wording, and only on the posts the plugin actually wrote. That is the EU AI Act (Article 50) transparency duty handled without you having to remember it.<\/p>\n\n<p><strong>Supported AI Providers<\/strong><\/p>\n\n<ul>\n<li><strong>OpenAI<\/strong> \u2014 All models supported<\/li>\n<li><strong>Anthropic<\/strong> \u2014 All models supported<\/li>\n<li><strong>Google Gemini<\/strong> \u2014 All models supported<\/li>\n<li><strong>OpenRouter<\/strong> \u2014 Access 200+ models including free tiers (Gemini Flash, Llama, Mistral, and more)<\/li>\n<li><strong>DeepSeek<\/strong> \u2014 All models supported (text generation)\nCheck <a href=\"https:\/\/antradusai.com\/antradus-ai-lite-models-tested\/\">our AI models recommendation list here <\/a><\/li>\n<\/ul>\n\n<p><strong>Key Features (free)<\/strong><\/p>\n\n<ul>\n<li><strong>Article from a keyword or URL<\/strong> \u2014 describe a topic, or paste any external link, and get a complete, structured, SEO-shaped article<\/li>\n<li><strong>SEO meta generation<\/strong> \u2014 focus keyword, SEO meta title and meta description, shown with Copy buttons ready for your SEO plugin<\/li>\n<li><strong>In-editor AI assistant<\/strong> \u2014 highlight text and rewrite, enhance, expand, shorten, fix grammar, translate, or run your own custom instruction (Classic and Block editor toolbars)<\/li>\n<li><strong>AI featured images<\/strong> \u2014 drawn from what the article is actually about, uploaded to your Media Library and set as featured in one click<\/li>\n<li><strong>10 image style presets<\/strong> (Default, Gaming, Medical, News, Sports, Finance, Tech, Food, Travel, Entertainment) \u2014 all editable with your own visual style prompts, plus an optional colour cast overlay<\/li>\n<li><strong>Image shape and quality<\/strong> \u2014 square, landscape or portrait, and a quality dial (OpenAI) so you control what each image costs you; it starts on Draft, the cheapest and fastest<\/li>\n<li>Every generated image is a full photograph that fills the frame \u2014 never a banner with empty colour bars or decorative shapes pasted over it<\/li>\n<li><strong>5 styles \u00d7 5 tones \u00d7 17 languages<\/strong><\/li>\n<li><strong>FAQ section generation<\/strong><\/li>\n<li><strong>AI disclosure line, on by default<\/strong> \u2014 one sentence at the very bottom of every article the plugin wrote: <em>\"This content was created with the help of AI (Antradus AI - gpt-4o).\"<\/em> It names the model that actually wrote that article, the wording is yours to edit, posts you wrote yourself are never marked, and any single post can opt out. Written for the EU AI Act (Article 50) transparency duty<\/li>\n<li><strong>Classic and Block editor<\/strong> \u2014 both editors, same features, no setup. Optionally disable Gutenberg for Posts<\/li>\n<li><strong>Five AI providers, your own key<\/strong> \u2014 OpenAI, Anthropic (Claude), Google Gemini, OpenRouter and DeepSeek, including OpenRouter's free models<\/li>\n<li><strong>Built-in documentation<\/strong> \u2014 browse every guide inside the plugin (Antradus AI \u2192 Docs), offline and always matching your installed version. The same guides are online at <a href=\"https:\/\/antradusai.com\/docs\/\">antradusai.com\/docs<\/a><\/li>\n<li><strong>Custom system prompt<\/strong> \u2014 standing instructions the AI follows for every article you generate<\/li>\n<li>Topic\/niche buttons for quick keyword entry<\/li>\n<li>SSRF-protected external URL fetching<\/li>\n<li>AI-powered correction of public figure names in keywords<\/li>\n<\/ul>\n\n<p><strong>Antradus AI Publisher \u2014 for working at scale<\/strong><\/p>\n\n<p><a href=\"https:\/\/antradusai.com\/for-publishers\/\">Antradus AI Publisher<\/a> is one license key away \u2014 the same plugin, nothing to reinstall. It unlocks the automation on top of everything above, and there is a <strong>7-day trial<\/strong>. See <a href=\"https:\/\/antradusai.com\/plugin-features\/\">every feature side by side<\/a>.<\/p>\n\n<ul>\n<li><strong>Human Voice<\/strong> \u2014 articles written the way people write: varied sentence rhythm, concrete detail instead of vague claims, no \"In conclusion\" endings, and an editable list of ~60 phrases the AI may never use (delve, in today's fast-paced, moreover, game-changer...). Applies to single posts, bulk publishing and product descriptions<\/li>\n<li><strong>Rotating article structures<\/strong> \u2014 three different section plans (classic explainer, question-led, ranked rundown) that the plugin cycles through, so a run of posts stops reading like the same template with different words in it. Set one shape site-wide, or override it per post<\/li>\n<li><strong>Write Like You<\/strong> \u2014 paste a few of your own published posts once; the AI extracts your style (rhythm, vocabulary, how you address readers, how you open and close) and writes in it from then on<\/li>\n<li><strong>One-click Humanize<\/strong> \u2014 rewrite a whole post, or just the paragraph you highlighted, so it stops reading like AI; every fact, link, image and section stays exactly where it was<\/li>\n<li><strong>Human Check<\/strong> \u2014 an instant score out of 100 listing the exact AI tells in your post (uniform sentence rhythm, hedging, passive voice, em dash overload, giveaway phrases). Runs offline: no AI request, no tokens, no cost<\/li>\n<li><strong>Bulk Publishing<\/strong> \u2014 paste up to 200 keywords or import a CSV and the AI writes and schedules every post, suggests topic ideas from your niche, and sorts posts into your categories; drip-schedule, review as drafts, retry failures, export client reports<\/li>\n<li><strong>Google Trends<\/strong> \u2014 see what your country is searching for right now (by category, active trends only, past 4 hours to 7 days) and write about any of it in one click. The article is built from the news reports Google Trends itself lists behind that trend: each one is fetched, read, and its publication time checked against the last 48 hours before a word is written. Anything older is dropped and named, and if nothing survives you are told exactly what was found and can paste your own source instead. Tick several trends and queue them all in one press, or open one and read every source verdict as it arrives. Optionally ends the article with the real list of sources it used. Needs a free SerpApi key<\/li>\n<li><strong>YouTube to Article<\/strong> \u2014 paste a video link and turn its transcript into an original article (with the free companion browser extension)<\/li>\n<li><strong>WooCommerce product generator<\/strong> \u2014 drop in a product photo and AI vision writes a titled, described, SEO-ready product<\/li>\n<li><strong>Yoast SEO &amp; Rank Math auto-fill<\/strong> \u2014 the generated focus keyword, title and description are inserted into your SEO plugin automatically, in both editors<\/li>\n<li><strong>Generate meta from any existing article<\/strong> with one click<\/li>\n<li><strong>Album generation<\/strong> \u2014 up to 9 distinct AI-designed scenes from your article, inserted as a gallery or featured image<\/li>\n<li><strong>Live web search<\/strong> \u2014 the AI researches the live web first, so you can cover news from hours ago<\/li>\n<li><strong>Merge 2 sources<\/strong> \u2014 blend two article URLs into one original piece<\/li>\n<li><strong>Free-form post assistant<\/strong> \u2014 tell the AI what to do with the whole post, in your own words<\/li>\n<li><strong>Internal linking<\/strong> \u2014 bulk batches link themselves together when they finish, and every post gets link suggestions in both directions: pages this one should link to, and older posts that should link back to it (the fix for orphan posts nothing points at). Links only ever wrap words already in your text \u2014 nothing is rewritten<\/li>\n<li><strong>SEO clusters<\/strong> \u2014 turn one idea, article link or video into a pillar-and-spoke set: a long overview plus 6-14 deep dives, planned for your approval, written, scheduled and linked to each other automatically, and filed together under one category the AI picks for the whole set<\/li>\n<li><strong>AI Search (GEO)<\/strong> \u2014 writes articles the way ChatGPT, Perplexity and Gemini can actually quote them: self-contained sections, real figures, dated facts, comparison tables. Includes an instant offline score of how quotable a post is, extra structured data handed to Yoast or Rank Math, a check of whether your site accidentally blocks the AI search crawlers, and optional counts of visits arriving from AI assistants<\/li>\n<li><strong>Search Demand<\/strong> \u2014 connects Google Search Console and Analytics and reads what this site already gets shown for, scores every search for whether that person would actually buy, writes the pages the good ones have nowhere to land, and rewrites the titles of posts aiming at searches nobody types.<\/li>\n<li><strong>Reporting<\/strong> \u2014 words, images, tokens and estimated cost per post, with editable model prices<\/li>\n<\/ul>\n\n<p><strong>Antradus AI Studio \u2014 for a whole show<\/strong><\/p>\n\n<p><a href=\"https:\/\/antradusai.com\/for-studios\/\">Antradus AI Studio<\/a> is everything in Publisher, plus a second pipeline: a podcast or video show, its whole back catalogue, and the things you publish around each episode. Publisher already turns a <strong>single<\/strong> video into an article from the post editor \u2014 Studio is that for an entire show, on a schedule.<\/p>\n\n<ul>\n<li><strong>Podcast to Articles<\/strong> \u2014 turn one episode into a set of articles that carry what you actually said. It asks what you are promoting \u2014 <strong>Spotify, YouTube, or both<\/strong> \u2014 and follows your answer instead of deciding for you. Spotify is the better source and says so: its transcript is punctuated and marks who is speaking, where YouTube's automatic captions do neither. Choose <strong>Both<\/strong> and you give both addresses and pick what your readers see: which player is embedded, which service the timestamps point at, and whether the show notes are read from both so a sponsor link one platform truncated is still found on the other. The transcript always comes from Spotify in that mode, shown as a tick you cannot undo. Timestamps can be moved onto YouTube's clock, and only by <strong>measuring<\/strong> the offset between the two recordings in dozens of places \u2014 never by assuming they start together, which they don't. The whole transcript is read (not the first few minutes), so every article is built from the episode's own arguments, figures and examples. <strong>Every<\/strong> quotation is checked word-for-word against the recording \u2014 the pull quotes and the ones inside sentences \u2014 and anything that doesn't match loses its quotation marks before the article is saved, so nothing is ever put in your guest's mouth. Where the recording labels its speakers, who said what is read off the recording; where it doesn't, or where a quotation runs across a change of speaker, the words are published without a name rather than guessed at. Claims can carry the moment they were said, as a link that starts the episode there. Every section is checked on its own for something that came off the recording \u2014 a quotation, a figure, a moment a reader can go and hear \u2014 and the ones that carry none are named for you. Every article embeds the video, links to the others, ends with a one-click <strong>Subscribe<\/strong> link, and can carry the episode's sponsors with a disclosure line and <code>rel=\"sponsored\"<\/code> links. Featured images can be built from the episode thumbnail \u2014 the same guest's face on every article, a new scene each time, with the thumbnail's headline removed and no new text added<\/li>\n<li><strong>Saved Plans<\/strong> \u2014 every episode you plan is kept, with the corrections you made on it: the speaker names you fixed, the quotations you ticked, the sponsor rows you edited. Open one again months later and the screen comes back exactly as you left it, without re-reading the episode and without paying for it again. Paste an address you have planned before and the plugin says so before you spend anything, and offers you that plan instead. Plans can be exported to a file and imported on another site, the recording is kept alongside each one so quotations can still be checked word for word years later, and a plan that has already written its articles says so \u2014 so opening it again cannot quietly publish the same episode twice<\/li>\n<li><strong>Episode Assets<\/strong> \u2014 a newsletter, a set of quote cards and the post copy, from an episode you have already planned. Nothing is read again and nothing is re-billed. <strong>The quote cards are drawn, not generated<\/strong>: the letters come from a font file, and every quotation is checked word for word against the recording in the instant before it is drawn \u2014 a card whose wording no longer matches is not produced at all, and says so. Four styles (flat, photo, split, and a highlighted-paper marker style), your own colours saved per show, and every card carries the moment it was said. The two styles drawn on the episode picture show you that picture first \u2014 taken from YouTube or Spotify, or uploaded by you when neither will give one up \u2014 rather than quietly falling back to flat. A quotation too long for a style falls back to a roomier one rather than being shrunk or trimmed \u2014 the words never give way, the design does. Right-to-left text is refused outright rather than drawn reversed. The newsletter comes out as real email HTML with a plain-text alternate, ready to copy, download, send yourself as a test, or push as a <strong>draft<\/strong> to Kit, Mailchimp or beehiiv \u2014 nothing here can send an issue. Slides download as a numbered ZIP with the caption, and can optionally be published straight to Instagram behind a confirmation that names the account and counts the slides<\/li>\n<\/ul>\n\n<p><strong>Antradus Managed \u2014 we run it for you<\/strong><\/p>\n\n<p>Not software. We build or enhance the site, run the back catalogue and hand you the finished thing. Sold after a conversation \u2014 <a href=\"https:\/\/antradusai.com\/contact\/\">talk to us<\/a>.<\/p>\n\n<p><strong>Where to read more<\/strong><\/p>\n\n<ul>\n<li><a href=\"https:\/\/antradusai.com\/plugin-features\/\">All plugin features<\/a> \u2014 every feature in Lite, Publisher and Studio, side by side<\/li>\n<li><a href=\"https:\/\/antradusai.com\/for-publishers\/\">Antradus AI for publishers<\/a> \u2014 bulk publishing, internal linking, SEO clusters and AI Search, for a site that has to keep producing<\/li>\n<li><a href=\"https:\/\/antradusai.com\/for-studios\/\">Antradus AI for studios<\/a> \u2014 a whole podcast or video back catalogue turned into articles, quote cards and newsletters<\/li>\n<li><a href=\"https:\/\/antradusai.com\/docs\/\">Documentation<\/a> \u2014 every guide, online; the same guides ship inside the plugin under Antradus AI \u2192 Docs<\/li>\n<li><a href=\"https:\/\/antradusai.com\/blog\/\">The Antradus AI blog<\/a> \u2014 what actually works in AI SEO, written from running it<\/li>\n<li><a href=\"https:\/\/antradusai.com\/antradus-ai-lite-models-tested\/\">Which AI models we recommend<\/a> \u2014 tested, with the ones to avoid<\/li>\n<\/ul>\n\n<!--section=installation-->\n<ol>\n<li>Install directly via the WordPress <strong>Plugins &gt; Add New<\/strong> screen, or upload the <code>antradus-ai-lite<\/code> folder to the <code>\/wp-content\/plugins\/<\/code> directory.<\/li>\n<li>Activate the plugin through the <strong>Plugins<\/strong> screen in WordPress.<\/li>\n<li>Open the new <strong>Antradus AI<\/strong> menu in your admin sidebar and enter your API key for your chosen provider.<\/li>\n<li>Open any post or page, find the <strong>Antradus AI<\/strong> panel, enter a keyword, and click <strong>Start Writing<\/strong>.<\/li>\n<\/ol>\n\n<!--section=faq-->\n<dl>\n<dt id=\"what%27s%20the%20difference%20between%20lite%2C%20publisher%20and%20studio%3F\"><h3>What's the difference between Lite, Publisher and Studio?<\/h3><\/dt>\n<dd><p><strong>Lite<\/strong> is free forever and is the whole writing toolkit: full articles from a keyword or any URL, SEO meta with copy buttons, the highlight-text assistant, and AI featured images. Most people never need more than this.<\/p>\n\n<p><strong>Publisher<\/strong> is for running a website at scale \u2014 bulk publishing, internal linking, SEO clusters, AI Search (GEO), Human Voice, live web search, YouTube to Article for a single video, automatic Yoast\/Rank Math fill and Reporting.<\/p>\n\n<p><strong>Studio<\/strong> is for running a <em>show<\/em>. It adds a second pipeline on top of Publisher: a whole podcast or video back catalogue turned into articles, with every quotation checked word-for-word against the recording, plus Saved Plans and Episode Assets (quote cards, newsletter drafts, Instagram).<\/p>\n\n<p>The short version: if you have a website, Publisher. If you have a podcast, Studio. Publisher already turns one video into an article, so you can try that shape before deciding.<\/p><\/dd>\n<dt id=\"do%20i%20install%20a%20different%20plugin%20for%20each%20plan%3F\"><h3>Do I install a different plugin for each plan?<\/h3><\/dt>\n<dd><p>No. There is one plugin. Lite comes from WordPress.org; Publisher and Studio are the same download, and your license key decides which features appear. Moving between plans means changing a key, never reinstalling anything, and your settings and API keys carry over.<\/p><\/dd>\n<dt id=\"i%20bought%20antradus%20ai%20pro%20before%20the%20plans%20existed%20%E2%80%94%20what%20happens%20to%20my%20license%3F\"><h3>I bought Antradus AI Pro before the plans existed \u2014 what happens to my license?<\/h3><\/dt>\n<dd><p>Nothing changes for you. The original license carries the <strong>full Studio<\/strong> feature set, permanently, and you don't need to do anything to keep it. No feature was taken away from anyone who had already paid.<\/p><\/dd>\n<dt id=\"is%20there%20a%20free%20trial%3F\"><h3>Is there a free trial?<\/h3><\/dt>\n<dd><p>Publisher has a 7-day trial with a card required. Studio is sold after a demo instead, because there is usually a real conversation to have about your show first. Lite is free forever and runs the same writing engine, so you can judge the output quality without any of that.<\/p><\/dd>\n<dt id=\"where%20can%20i%20see%20everything%20publisher%20and%20studio%20add%3F\"><h3>Where can I see everything Publisher and Studio add?<\/h3><\/dt>\n<dd><p>Three places, and they all say the same thing. Inside the plugin, open <strong>Antradus AI \u2192 \u2728 More Features<\/strong>: every feature in all three plans, with the ones your license does not cover marked with a padlock, so you can see exactly what you would get before you spend anything. Online, there is <a href=\"https:\/\/antradusai.com\/plugin-features\/\">the full feature list<\/a> side by side, plus a page for each plan \u2014 <a href=\"https:\/\/antradusai.com\/for-publishers\/\">Antradus AI for publishers<\/a> if you run a website, and <a href=\"https:\/\/antradusai.com\/for-studios\/\">Antradus AI for studios<\/a> if you run a podcast or video show.<\/p><\/dd>\n<dt id=\"where%20is%20the%20documentation%3F\"><h3>Where is the documentation?<\/h3><\/dt>\n<dd><p>Both inside the plugin and online. <strong>Antradus AI \u2192 Docs<\/strong> carries every guide, offline, always matching the version you have installed \u2014 there is nothing to configure and no internet needed. The same guides are published at <a href=\"https:\/\/antradusai.com\/docs\/\">antradusai.com\/docs<\/a>, which is the easier one to link to a colleague. Practical write-ups on what actually works in AI SEO live on <a href=\"https:\/\/antradusai.com\/blog\/\">the Antradus AI blog<\/a>.<\/p><\/dd>\n<dt id=\"can%20i%20try%20the%20paid%20features%20before%20paying%3F\"><h3>Can I try the paid features before paying?<\/h3><\/dt>\n<dd><p>Publisher has a <strong>7-day trial<\/strong> (a card is required, and you are billed only if you stay past day 7). Studio is sold after a demo instead, because there is usually a real conversation to have about your show first \u2014 <a href=\"https:\/\/antradusai.com\/contact\/\">talk to us<\/a>. Lite is free forever and runs the exact same writing engine, so you can judge the output quality without any of that.<\/p><\/dd>\n<dt id=\"where%20do%20i%20find%20the%20plugin%20while%20editing%20a%20post%3F\"><h3>Where do I find the plugin while editing a post?<\/h3><\/dt>\n<dd><p>In the Classic editor it appears as a panel under the content area. In the block editor it lives in the right-hand sidebar \u2014 click the anchor (Antradus AI) icon in the top toolbar (or the three-dots menu, then Antradus AI) to open it.<\/p><\/dd>\n<dt id=\"which%20api%20key%20do%20i%20need%3F\"><h3>Which API key do I need?<\/h3><\/dt>\n<dd><p>You need an API key from at least one supported provider:<\/p>\n\n<ul>\n<li><a href=\"https:\/\/platform.openai.com\/\">OpenAI<\/a><\/li>\n<li><a href=\"https:\/\/console.anthropic.com\/\">Anthropic<\/a><\/li>\n<li><a href=\"https:\/\/aistudio.google.com\/\">Google AI Studio<\/a><\/li>\n<li><a href=\"https:\/\/openrouter.ai\/\">OpenRouter<\/a> \u2014 offers free models requiring only a free account<\/li>\n<\/ul><\/dd>\n<dt id=\"does%20this%20plugin%20store%20my%20content%20on%20external%20servers%3F\"><h3>Does this plugin store my content on external servers?<\/h3><\/dt>\n<dd><p>No. Your keywords and articles are sent directly to the AI provider you have configured. This plugin does not store, log, or transmit your data to any server other than the provider you choose. Refer to each provider's privacy policy for details on how they handle request data.<\/p><\/dd>\n<dt id=\"how%20do%20the%20seo%20meta%20and%20my%20seo%20plugin%20work%20together%3F\"><h3>How do the SEO meta and my SEO plugin work together?<\/h3><\/dt>\n<dd><p>The free version generates the focus keyword, SEO title, and meta description and shows them with Copy buttons \u2014 paste each value into Yoast SEO, Rank Math, or any other SEO plugin. In <strong>Publisher<\/strong> the values are inserted into Yoast or Rank Math automatically, in both editors.<\/p><\/dd>\n<dt id=\"how%20does%20the%20in-editor%20ai%20assistant%20work%3F\"><h3>How does the in-editor AI assistant work?<\/h3><\/dt>\n<dd><p>Highlight any text while writing. In the Classic editor, open the <strong>AI \u2728<\/strong> dropdown in the toolbar; in the Block editor, it appears in the block's text toolbar. Pick Rewrite, Enhance, Expand, Shorten, Fix Grammar, Translate, or type your own instruction \u2014 the highlighted text is replaced with the result (Ctrl+Z brings the original back).<\/p><\/dd>\n<dt id=\"does%20image%20generation%20work%20with%20all%20providers%3F\"><h3>Does image generation work with all providers?<\/h3><\/dt>\n<dd><p>Image generation is available via OpenAI (gpt-image\/DALL-E 2 \/ DALL-E 3), Google Gemini (Imagen), and OpenRouter (Flux and compatible models). Anthropic does not offer an image generation API.<\/p><\/dd>\n<dt id=\"can%20i%20use%20a%20free%20ai%20model%3F\"><h3>Can I use a free AI model?<\/h3><\/dt>\n<dd><p>Yes. OpenRouter provides access to free models such as Google Gemini Flash and others. Select OpenRouter as your provider, create a free account at openrouter.ai, and choose a free model in the settings.<\/p><\/dd>\n<dt id=\"can%20i%20customize%20the%20writing%20style%3F\"><h3>Can I customize the writing style?<\/h3><\/dt>\n<dd><p>Yes. You can set a custom system prompt in the <strong>Antradus AI<\/strong> admin menu to define the writing style, persona, language, or any standing instructions the AI should follow for every article.<\/p><\/dd>\n<dt id=\"how%20does%20youtube%20to%20article%20work%3F%20%28publisher%29\"><h3>How does YouTube to Article work? (Publisher)<\/h3><\/dt>\n<dd><p>In <strong>Publisher<\/strong>, install the free companion browser extension, the <strong>Antradus Auto Pilot YT extension<\/strong>, and enable it on your WordPress site. Paste a YouTube link into the panel, click <strong>Get transcript<\/strong> \u2014 the extension reads the video's transcript inside your own browser \u2014 review it, then click <strong>Start Writing<\/strong> to turn it into an original article. Videos with subtitles (CC) give the best results.<\/p><\/dd>\n<dt id=\"how%20does%20album%20generation%20work%3F%20%28publisher%29\"><h3>How does album generation work? (Publisher)<\/h3><\/dt>\n<dd><p>Open <strong>Album Generating<\/strong> in the panel, choose how many images you want (up to 9), and click Generate Album. The AI reads your article, designs a different scene for each image, and draws them one by one. Click any image to set it as featured, or insert them all as a gallery.<\/p><\/dd>\n<dt id=\"does%20ai-written%20content%20sound%20obviously%20ai-written%3F%20%28publisher%29\"><h3>Does AI-written content sound obviously AI-written? (Publisher)<\/h3><\/dt>\n<dd><p>That is what <strong>Human Voice<\/strong> in <strong>Publisher<\/strong> is for. It tells the AI to vary sentence length instead of writing every sentence the same length, to open on something specific, to use concrete numbers and names instead of vague claims, to skip the summary paragraph at the end, and to never use around 60 giveaway phrases (you can edit that list). You can also teach it your own style from your published posts, rewrite any existing post with one click, and run an instant <strong>Human Check<\/strong> that scores the post and names every tell it finds \u2014 no AI request, so that check costs nothing.<\/p>\n\n<p>There is a second giveaway that good sentences alone never fix: every post coming out in the same shape. Two articles on different subjects, with the same opening move and the same run of sections, read as mass-produced however well each sentence is written. <strong>Rotating article structures<\/strong> answers that \u2014 three different section plans that the plugin cycles through, so consecutive posts are built differently, not just worded differently.<\/p>\n\n<p>One thing it deliberately does not do: it never invents personal anecdotes, statistics, or customer quotes to sound human, because that would publish false claims in your name. The final five minutes \u2014 adding the real detail only you know \u2014 are still yours.<\/p><\/dd>\n<dt id=\"does%20it%20work%20with%20the%20classic%20editor%3F\"><h3>Does it work with the Classic Editor?<\/h3><\/dt>\n<dd><p>Yes. The plugin automatically detects whether a post uses the Block Editor or the Classic Editor and loads the correct interface.<\/p><\/dd>\n<dt id=\"will%20it%20conflict%20with%20other%20ai%20plugins%3F\"><h3>Will it conflict with other AI plugins?<\/h3><\/dt>\n<dd><p>The plugin uses a unique <code>antradus_<\/code> option prefix and <code>antradus_lite_<\/code> function prefix throughout.<\/p><\/dd>\n\n<\/dl>\n\n<!--section=changelog-->\n<h4>2.10.0<\/h4>\n\n<ul>\n<li><strong>Added (Publisher): Search Demand \u2014 what you already rank for, and what to do about it.<\/strong> A new <strong>&#128269; Demand<\/strong> tab on the Bulk Publishing page connects your own Google Search Console (and optionally Analytics), reads what this site is <em>already being shown for<\/em>, and turns it into two lists with a button on each. Not a keyword tool: it answers \"what should I write about\" from your own impression data \u2014 the only source that knows what Google already thinks your site is about \u2014 rather than from search volume bought from somebody else.<\/li>\n<li><strong>Every search is scored for whether that person would actually buy.<\/strong> You describe what you sell in one plain paragraph, and each search is rated 0-3 on the person typing it, not the topic. This is the part that matters: a site can collect a year of impressions from an audience that will never buy anything, and without this filter the obvious next step is to write more of the same. The rejected searches stay visible with the reason each was rejected, because seeing what was thrown away is how you know whether to trust the filter.<\/li>\n<li><strong>\"Write these\"<\/strong> \u2014 searches you get impressions for that no page of yours aims at. Tick them and they become ordinary bulk articles, each one's focus keyphrase set to the exact search it was written for. Live web search is off by default here, deliberately unlike Trends: a commercial search does not postdate the model's training data, so paying for one would buy nothing.<\/li>\n<li><strong>\"Fix these\"<\/strong> \u2014 posts that are indexed and being seen, but whose title aims at something nobody types, or that rank on page one or two and earn far fewer clicks than that position normally does. <strong>Only the two lines Google shows are ever changed<\/strong> \u2014 the article, its heading and its web address are never touched \u2014 every rewrite is shown to you as before-and-after before anything is saved, and <strong>one button puts the whole run back<\/strong>.<\/li>\n<li><strong>It refuses the advice it cannot stand behind.<\/strong> A page Google has never indexed is reported separately and offered no title fix, because that is an indexing problem and a new title would not touch it. A page losing impressions as well as clicks is told plainly that it is losing positions and needs the article updating, not a new title. And if the AI proposes a keyphrase your page does not actually get impressions for, the suggestion is refused rather than quietly corrected \u2014 inventing a phrase nobody searches is the exact fault the feature exists to fix.<\/li>\n<li><strong>Set up with a Google service account<\/strong>, so nothing is shared with anyone and no third-party app needs approving. The screen shows the address to give read access to, names which Google API is switched off when one is, and tells you if your server's clock is what Google is objecting to.<\/li>\n<li><strong>Fixed (Publisher): Google Trends and SEO clusters were logged as \"other\" in Reporting.<\/strong> Both make model calls, and neither was named in the usage log, so their cost appeared under a heading that explained nothing. They now report as <em>Trending article<\/em> and <em>Cluster planning<\/em>.<\/li>\n<li><strong>Added (all editions): \u2728 More Features \u2014 one screen that shows you what the other plans do.<\/strong> Until now, a free install could only see the paid features that happen to sit beside a free control. Everything living on a screen of its own \u2014 Bulk Publishing, Google Trends, SEO clusters, Reporting, and the whole podcast pipeline \u2014 was simply invisible, so the honest answer to \"what would I get\" was \"go and read the website\". Now <strong>Antradus AI \u2192 \u2728 More Features<\/strong> lists every feature in Lite, Publisher and Studio, with a tick beside the ones your license already covers and a padlock beside the ones it doesn't. Publisher installs see only what Studio adds; Studio installs are not shown the screen at all, because there is nothing left to sell them.<\/li>\n<li><strong>Bulk Publishing and Reporting now appear in the free menu, locked.<\/strong> They sit exactly where they appear on a paid plan, so the free menu is the paid menu with padlocks on it rather than a different shape. Both are links to the More Features screen \u2014 nothing here opens a page that renders an error or an empty table.<\/li>\n<li><strong>Nothing moved across the free\/paid line.<\/strong> Every feature that was free is still free, and nothing that was paid became free or vice versa. This release adds visibility, not entitlement.<\/li>\n<li><strong>The feature list now lives in one place.<\/strong> The screen, this readme and the documentation are generated from a single list in the plugin, and a test fails the build if the three ever disagree \u2014 so the plugin can no longer advertise a feature it dropped, or quietly ship one it never mentioned.<\/li>\n<li><strong>New guide: \"Which Plan Do I Need?\"<\/strong> \u2014 Lite vs Publisher vs Studio vs Managed, what each one is actually for, and how to decide. Readable inside the plugin under <strong>Antradus AI \u2192 Docs<\/strong>, and online at <a href=\"https:\/\/antradusai.com\/docs\/\">antradusai.com\/docs<\/a>.<\/li>\n<li><strong>More signposting to the things that explain this plugin<\/strong> \u2014 <a href=\"https:\/\/antradusai.com\/plugin-features\/\">the full feature list<\/a>, <a href=\"https:\/\/antradusai.com\/for-publishers\/\">for publishers<\/a>, <a href=\"https:\/\/antradusai.com\/for-studios\/\">for studios<\/a>, <a href=\"https:\/\/antradusai.com\/docs\/\">the documentation<\/a> and <a href=\"https:\/\/antradusai.com\/blog\/\">the blog<\/a> are now linked from the readme, the docs and the new screen, instead of being something you had to already know about.<\/li>\n<\/ul>\n\n<h4>2.9.0<\/h4>\n\n<ul>\n<li><strong>Added (all editions): the AI disclosure line.<\/strong> Every article the plugin writes now ends with one sentence telling readers it was written with AI, and naming the model that wrote it \u2014 <em>\"This content was created with the help of AI (Antradus AI - gpt-4o).\"<\/em> On by default, because the EU AI Act (Article 50) asks anyone publishing AI-generated text to say so, and that duty does not belong to a paid plan.<\/li>\n<li><strong>It names the model that actually wrote that article.<\/strong> The model is recorded on the post as it is written, so switching provider next month does not rewrite the history of what you published last month.<\/li>\n<li><strong>Only the posts Antradus wrote.<\/strong> Articles from the editor, from Bulk Publishing (clusters, Trends and podcast spin-offs included) and product copy written from a photo. Posts you wrote yourself are never marked, a CSV import is never marked, and using the AI Assistant or Human Voice to edit your own writing does not mark it either.<\/li>\n<li><strong>Yours to word, and to switch off.<\/strong> Antradus AI \u2192 Settings \u2192 <strong>AI Disclosure<\/strong>: turn it off, or rewrite the sentence with <code>[model]<\/code> and <code>[provider]<\/code> placeholders, and every article follows at once \u2014 the line is added when the page is read, never written into your post content, so nothing can delete it by accident and nothing is left behind if you turn it off. Any single post can opt out from its own <strong>AI Disclosure<\/strong> box in the editor.<\/li>\n<li><strong>Changed (Publisher): a Google Trends source now counts as fresh if it was published in the last 48 hours<\/strong>, counted back from right now rather than rounded to a calendar day. The old \"published today\" rule accepted half an hour of reporting at 00:30 and threw away last night's report on the story still trending this morning. The tighter settings are unchanged in spirit and now read as <em>within 12 hours of the trend<\/em> and <em>within 6 hours of the trend<\/em>, both on top of the 48-hour floor; an install that had chosen \"published today\" moves to the 48-hour setting rather than to a stricter one. Times shown to you are still your site's local time.<\/li>\n<\/ul>\n\n<h4>2.8.0<\/h4>\n\n<ul>\n<li><strong>Added (Publisher): Google Trends, with the freshness actually checked.<\/strong> A new <strong>\ud83d\udcc8 Trends<\/strong> tab on the Bulk Publishing page shows what your country is searching for right now \u2014 country, past 4 hours to 7 days, category, active trends only, search volume and how fast each one is climbing. Press <strong>Write about this topic<\/strong> on any row and Antradus pulls the news reports Google Trends itself lists behind that trend, then does the part nobody else does: it <strong>fetches each report, reads the publication time out of the page<\/strong> (structured data, article:published_time, the article's own time tag) and keeps only what was published <strong>today in your site's timezone<\/strong>. Live web search is always on for these, so the model can confirm and fill gaps \u2014 but the checked reports are the spine, and it is told not to outrun them.<\/li>\n<li><strong>When nothing is fresh enough, it says so and hands you the controls.<\/strong> Instead of writing a confident article from a model's memory, the tab tells you how many sources it looked at, which was the newest, and when it was published \u2014 then offers a box to paste your own source, which goes through exactly the same check. Nothing is queued until at least one source has passed.<\/li>\n<li><strong>The list of sources is real.<\/strong> Optionally ends each trend article with the reports it was actually written from \u2014 outlet, headline and publication time \u2014 built by the plugin from the pages it read, never written by the AI. The full record, including the sources that were checked and dropped and why, is kept on the post itself.<\/li>\n<li><strong>Write about ten trends without ten trips through the screen.<\/strong> Tick the trends you want, press <strong>\u26a1 Add to the queue<\/strong>, and each one is checked and queued in turn against your saved settings \u2014 style, tone, language, post type, category, author \u2014 with a running count and a <strong>Stop<\/strong> button that finishes the trend in hand and leaves the rest. They all land in one batch, so the Queue tab runs and reports them together. Your choices are remembered the first time, so tomorrow morning is one click.<\/li>\n<li><strong>New settings<\/strong> (Antradus AI \u2192 Settings \u2192 Google Trends): your SerpApi key with a <strong>Test connection<\/strong> button that reports how many searches your plan has left without spending one, a default country, how many sources one article may use (never two from the same outlet), and how fresh a source must be \u2014 published today, or within 12 or 6 hours of the trend.<\/li>\n<\/ul>\n\n<h4>2.7.0<\/h4>\n\n<ul>\n<li><strong>Two paid plans instead of one.<\/strong> <strong>Publisher<\/strong> is everything for a website \u2014 bulk publishing, internal linking, SEO clusters, AI Search, Human Voice, YouTube to Article, and the rest. <strong>Studio<\/strong> adds the whole show pipeline on top: Podcast to Articles, Saved Plans and Episode Assets. Antradus AI Lite is unchanged and stays free forever.<\/li>\n<li><strong>Nobody loses anything they already bought.<\/strong> Every existing licence carries the full Studio feature set, by licence number as well as by name, so a rename can never quietly take a feature away from someone who paid for it.<\/li>\n<li><strong>A 7-day free trial on Publisher.<\/strong> There was no trial at all before, because the only plan was a one-time payment and a trial on one of those bills the whole amount the day it ends. Publisher is monthly, which is what makes a trial safe \u2014 and it is 7 days rather than 3, because nothing about search is visible in 3.<\/li>\n<li>On Publisher, the Podcast to Articles and Episode Assets tabs are shown locked rather than hidden, so it is clear what Studio adds and what it costs \u2014 and they link to a person, not just a checkout.<\/li>\n<li>Internal: the plan check matches the plan name exactly and never falls back to the licensing SDK's ranked comparison, which a trial can outrank. Anything the plugin cannot positively identify is treated as Publisher, never as Studio.<\/li>\n<\/ul>\n\n<h4>2.6.0<\/h4>\n\n<ul>\n<li>Added (Pro): <strong>Saved Plans.<\/strong> A planned episode is now kept instead of evaporating. Reading a three-hour episode is around twenty requests, and the plan screen is where a <em>person<\/em> fixes what no code can \u2014 who is speaking, a misheard name, which quotations are worth printing, a sponsor row that came through wrong. Until now all of that lived in a twelve-hour session and was then gone: opening the same episode a week later meant paying to read it again and re-doing every correction by hand.<\/li>\n<li>A new <strong>\ud83d\udcbe Saved Plans<\/strong> tab beside Podcast to Articles lists everything you have planned \u2014 service, show, episode, guest, how many articles and quotations, roughly what it cost \u2014 and filters by service, show and date. <strong>Load<\/strong> puts a plan back on the podcast screen exactly as you left it. Nothing is re-read and nothing is charged.<\/li>\n<li>Plans save two ways: a <strong>\ud83d\udcbe Save this plan<\/strong> button, and automatically when you press the button that writes the articles \u2014 which is the moment a plan is finished being corrected, and also the moment a person stops thinking about it.<\/li>\n<li><strong>Paste an episode you have planned before and the plugin tells you before you spend anything<\/strong>, and offers to open that plan instead of reading it again. It recognises the same episode from a share link, a watch link, a link with a timestamp on it, or the bare id.<\/li>\n<li><strong>The recording is kept with each plan<\/strong>, compressed. The copy stored beside an episode is cleaned up after thirty days; the one in the plan is not, so quotations in a plan opened next year can still be checked word for word against what was actually said. It can be turned off, and the tab shows what the plans are costing you in storage either way.<\/li>\n<li>A plan that has <strong>already written its articles says so<\/strong> when you open it, and how many \u2014 so reloading one cannot quietly publish the same episode a second time.<\/li>\n<li>Plans can be <strong>exported to a file and imported on another site<\/strong>, which also makes a problem plan something you can send us.<\/li>\n<li>Two refusals, both deliberate. A plan saved by a different version of the plugin is <strong>refused by name<\/strong>, saying both formats, rather than loaded with fields silently missing \u2014 a plan that comes back three fields short is worse than one that will not come back. And if the plan is too large for your host's database to store the recording alongside it, the <strong>plan is saved without the recording<\/strong> and tells you, rather than the save failing and taking your corrections with it.<\/li>\n<li>Saved plans are <strong>not<\/strong> deleted when the plugin is uninstalled unless you explicitly tick a box asking for that. Months of your own corrections are not something an uninstall should quietly take with it.<\/li>\n<li><p>Nothing in the shipped Podcast to Articles pipeline changed. Quote verification, timestamp mapping, the measured clock offset, attribution, article writing and the render layer are byte-for-byte what they were.<\/p><\/li>\n<li><p>Changed: <strong>the whole interface has been redrawn, and nothing has moved.<\/strong> Every screen \u2014 the post editor box, Settings, Bulk Publishing, Reporting \u2014 was built at a different point in this plugin's life and looked it: the same field was three different heights, the same blue was four blues, and on the Bulk screen the button that actually creates your posts was the same grey as <em>Restore default<\/em>. There is now one set of colours, corners, shadows and control heights behind all of them. Fields, buttons and tables match wherever you are; the action a form exists for looks like the action a form exists for; tabs join the panel they open; tables get a readable head and a row that follows your pointer; the Reporting figures are set as figures; hints are quieter, and the ones that are warnings look like warnings. Every control has a proper keyboard focus ring, and animation is switched off for anyone whose system asks for that. <strong>Not a single thing changed place<\/strong> \u2014 every element on all five screens is in the same order and the same column it was in before, which was checked element by element rather than by eye.<\/p><\/li>\n<li><p>Added (Pro): <strong>Episode Assets<\/strong> \u2014 one more step after the plan, producing the things an episode needs that are not articles.<\/p><\/li>\n<li><strong>Quote cards, drawn rather than generated.<\/strong> Every competitor's quote images are AI-selected and AI-transcribed, and nobody checks them. These are composed by the server from a font file, and each quotation is re-checked against the recording in the instant before it is drawn \u2014 through the same checker the articles use, not a second copy of it. Change one character of a verified quotation and no card is produced at all. Four styles: flat, the episode picture behind the words, a split with the picture above, and a highlighted-paper marker style whose strokes are measured off each line rather than stamped out as identical rectangles.<\/li>\n<li><strong>The design gives way, never the words.<\/strong> A quotation too long for a style falls back to a roomier one and tells you it did. It is never shortened, re-punctuated or squeezed into unreadable type to fit. Right-to-left text is refused with an explanation rather than drawn reversed and unshaped, which is what the drawing library would otherwise do.<\/li>\n<li><strong>Your colours, saved per show<\/strong> \u2014 seven of them, plus four one-click presets, contrast warnings against the accessibility threshold (a warning, never a block), and a button that reads five colours out of the episode picture for you to assign. Two open-licensed typefaces ship with the plugin, and your own can be uploaded \u2014 checked at upload for the quotation marks and dashes a quote card needs, so you find out then rather than after a card goes out with empty boxes in it.<\/li>\n<li><strong>The episode picture is its own step, on screen before you choose a style.<\/strong> Two of the four styles are drawn on it, so the panel shows you the picture it has \u2014 where it came from and how big it is \u2014 instead of letting you pick Photo and find out ten cards later that they all came out flat. It is taken from the episode itself (YouTube's 16:9 still when the run has a YouTube address, Spotify's cover art otherwise), fetched once and kept in your Media Library. If neither service will give one up, the reason says so and <strong>you can upload your own<\/strong>, which the cards, the preview and the colour picker then all use. Styles that need a picture are offered but not selectable until there is one, with the reason written beside them.<\/li>\n<li><strong>The preview is the real card<\/strong>, rendered by the same code that writes the file and scaled down in the browser \u2014 not a JavaScript approximation that disagrees with it about where a line wraps.<\/li>\n<li><strong>A newsletter<\/strong> built from the episode: verified quotations with the timestamp linked to the moment, your articles, the sponsor block with its disclosure, and a subscribe row. Real email HTML \u2014 tables, inline styles, 600px, a plain-text alternate \u2014 in whichever shape your provider actually wants, because sending the wrong one produces something that looks perfect in the provider's preview and breaks in real inboxes. Copy it, download it, or send yourself a test, all of which work with any provider on earth.<\/li>\n<li><strong>Kit, Mailchimp and beehiiv<\/strong> create a <strong>draft<\/strong>. There is no send button anywhere in this plugin and no code path that could reach one. beehiiv's API restricts creating posts to Enterprise plans, so that one is expected to refuse on most accounts \u2014 it says so plainly and points you at Copy HTML instead of failing mysteriously.<\/li>\n<li><strong>Instagram, optional and off until you set it up.<\/strong> Instagram has no drafts, so publishing is immediate and public \u2014 it asks you to confirm, naming the account and counting the slides, every time. Before a single slide is uploaded it checks that Instagram can actually download your images, which is what stops a half-built carousel on a local, staging or password-protected site. The ten-slide API limit is enforced in the interface with the reason, and the daily posting limit is read from your own account rather than guessed at.<\/li>\n<li><strong>Post copy for Instagram, LinkedIn and X<\/strong> in one request, with hashtags built from the people the episode actually names. The AI writes the words around the quotation and never the quotation itself.<\/li>\n<li><strong>Context lines are the only part that costs anything<\/strong> \u2014 one request per card, stated on screen before you commit. The AI sees ninety seconds either side of the quotation and nothing else, and what comes back is checked in code for quotation marks, invented figures, outside names, links and phrases lifted off the recording. Anything that fails is thrown away and the card is drawn quote-only. It is never patched up to pass.<\/li>\n<\/ul>\n\n<h4>2.5.11<\/h4>\n\n<ul>\n<li>Fixed (Pro): <strong>a Spotify-only episode showed no quotations at all.<\/strong> The recording was read perfectly \u2014 the voices labelled, the caption timings exact, every quotation checked word for word against it \u2014 and then the plan screen drew none of them. The quotations table, and the <em>Who is speaking<\/em> step above it, were shown only when the plan had found <strong>two or more named people<\/strong>; on a Spotify-only run it never does, because who is on an episode is read out of the show notes and Spotify's notes are refused (it serves a truncated share preview, not your description). The articles then lost the quotes too: one nobody can be named for reaches the writer marked <em>speaker unknown<\/em>, and a writer told that will often leave it out. Both mode was unaffected throughout, because the YouTube half supplies the notes \u2014 which is why the same episode showed its quotes there and not here.<\/li>\n<li>The question is now asked because <strong>the recording<\/strong> says there are two voices, not because we managed to guess their names \u2014 the sensible order, given that guessing them is the part that fails. Where there is no list to pick from, <em>Who is speaking<\/em> gives you a box to type each name into, beside the first line that voice actually says and a link to hear it. Where the plan did find the people, the dropdown is exactly as it was.<\/li>\n<li>A voice you leave blank stays blank. In particular, on a two-voice episode with <strong>one<\/strong> name filled in, the other voice's quotations are no longer handed that single name \u2014 they are published with no name, as they should be. That path could not arise while the table was hidden, and would have printed one speaker's words under the other's the moment it was shown.<\/li>\n<li>A quotation whose speaker is not on the offered list is no longer thrown away \u2014 the words passed the check against the recording, so it is kept and published unattributed. Losing a verified quotation over an unrecognised name was the wrong half to lose.<\/li>\n<\/ul>\n\n<h4>2.5.10<\/h4>\n\n<ul>\n<li>Changed (Pro): <strong>in Both mode, a timestamp that was moved onto the other service's clock now opens the player two seconds early.<\/strong> Those seconds are measured, not read off the recording the words came from, and a measurement is good to about a second either way \u2014 the anchors are caption chunks, and a caption chunk starts where the chunk starts, not where the sentence does. So a line Spotify puts at 0:05 lands at 0:04 or 0:06 on YouTube, and there is no way to know from here which one it is.<\/li>\n<li>The two mistakes are not worth the same. A second <strong>late<\/strong> opens the player mid-sentence or past the line entirely, and the one reader who checks a quotation concludes it was invented. Two seconds <strong>early<\/strong> costs them the tail of the previous sentence, which is what anyone scrubbing to a quotation does by hand anyway. So the link now aims deliberately at the harmless side.<\/li>\n<li>The <strong>printed<\/strong> time does not move with it: the number in the article is still the moment the words were said, because that is what the article is claiming and it is the true one. The run-up applies only to links that were translated between two recordings \u2014 a single-service episode's timestamps are read straight off the recording you are being sent to and are unchanged.<\/li>\n<\/ul>\n\n<h4>2.5.9<\/h4>\n\n<ul>\n<li>New (Pro): <strong>you can now name the speaker on a quotation the recording refuses to attribute.<\/strong> A line that starts in one person's turn and ends in the next carries no speaker label, so the plan screen printed <em>\"Not named \u2014 this line crosses a change of speaker\"<\/em> and left it there: unticked, greyed out, and nothing you could do about it. That is the honest reading of the transcript and it is still what the row leads with \u2014 but <em>the recording cannot say<\/em> is not <em>nobody can<\/em>. Very often the second turn is an interruption or a \"yeah, exactly\" and the line really is one person's, which anyone who heard the episode settles in four seconds. Those rows now carry their own dropdown of the people in the episode, underneath the recording's own answer.<\/li>\n<li>It starts on <strong>Leave it unnamed<\/strong>, so nothing changes if you ignore it and the row still arrives unticked. Name somebody and the row ticks itself and is published under that name \u2014 your answer outranks everything else in the plugin, exactly as it already did on a YouTube episode. Naming a voice in <em>Who is speaking<\/em> never reaches these rows and never overwrites an answer you gave here: they belong to no voice, which is the whole reason they had to be asked about separately. Every other row on a labelled recording is unchanged and still has no dropdown \u2014 that column reports what the recording said, and it is not there to be argued with.<\/li>\n<li>Fixed (Pro): <strong>the suggested names for \"Speaker 1\" and \"Speaker 2\" could come out backwards on exactly the episodes where it matters.<\/strong> The guess reads who says whose name \u2014 a host says the guest's name constantly and almost nobody says their own \u2014 and that count was taken per episode rather than per thousand words. A voice holding three quarters of the recording therefore picks up more of every term simply by being longer, the guest's own name included, because a diariser that lumps the interviewer's question into the guest's block files that name under the guest. The count is now a rate, and the majority voice is never named the host: an interviewer who talks two thirds of the time is rare, that lumping is not. Where the two signals disagree the share wins, the reason on screen says the count disagreed, and the row is marked as the one to check first.<\/li>\n<li>Fixed (Pro): <strong>a reason that contradicted the number printed beside it.<\/strong> With two voices in the room, whichever one was left over was described as doing \"most of the answering\" whatever its share \u2014 so a row could read <em>\"does most of the answering. 38% of the talking\"<\/em> in one sentence. It now says that only when it is true.<\/li>\n<li>Changed (Pro): the <em>First heard<\/em> column on the voices table is now <strong>Hear this line<\/strong>, and the time is the moment of the line quoted on that row rather than the first noise the voice makes. A voice opens with \"wrong, beginner's luck\" far more often than with a sentence, and four seconds there identify nobody \u2014 which is the opposite of what the column is for.<\/li>\n<li>Fixed: the voices step had a test written for it that was never added to the suite, so it had never once run. That is how the backwards guess above reached a real episode.<\/li>\n<\/ul>\n\n<h4>2.5.8<\/h4>\n\n<ul>\n<li>Changed (Pro): <strong>podcast articles are now as long as the episode gave them, and no longer.<\/strong> There was a word target \u2014 900-1400 for a spin-off, 2000-3000 for the episode article \u2014 and a stretch of conversation carrying one projection and three quotations cannot fill it honestly. So it was filled dishonestly: one measured article ran to 1,483 words in which the same population projection was restated under four of its six headings, its timestamp printed five times, its two years eight times each, and the focus keyphrase used fourteen times with all six headings carrying it.<\/li>\n<li>None of that was the writer breaking a rule. Every anti-repetition rule was already there and every one of them lost to the number, because a length target on material of unknown size is an instruction to pad. The target is gone. The size is counted from what that article was actually given \u2014 its verified quotations, figures, the speaker's own qualifications and the objections put to them \u2014 at roughly one section per two of those, and the article stops when the material does. Expect shorter articles, and expect the same episode to produce articles of noticeably different lengths.<\/li>\n<li>Fixed (Pro): <strong>two headings counts contradicted each other.<\/strong> The spin-off rule asked for four to six sections while the running-order shapes asked for \"5 to 7\" and \"4 to 7\" \u2014 and the shapes were added to the prompt last, so the looser number won every time. The size rule is now the final word on it.<\/li>\n<li>Changed (Pro): <strong>counts that were per-section are now per-article.<\/strong> A per-section allowance is an allowance a writer spends: \"one keyphrase per section\" across six sections produced fourteen uses, and \"at least one short sentence per section\" produced a third of the article in clipped fragments. The keyphrase is now three times in the whole article and at most one heading; short sentences are fewer than one in eight, never two side by side. Each figure and each timestamp is used once and never repeated.<\/li>\n<li>Changed (Pro): the writing brief now comes <strong>before<\/strong> the rules rather than after them, and says plainly that the rules are a floor rather than the assignment. The prompt had grown to roughly ninety prohibitions, and an article that breaks none of them can still  &hellip;<\/li>\n<\/ul>","raw_excerpt":"Free AI article writer for WordPress: complete SEO-optimized articles and AI featured images from a keyword or URL, inside the editor.","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin\/308029","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin"}],"about":[{"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/types\/plugin"}],"replies":[{"embeddable":true,"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/comments?post=308029"}],"author":[{"embeddable":true,"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wporg\/v1\/users\/ehabahmad"}],"wp:attachment":[{"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/media?parent=308029"}],"wp:term":[{"taxonomy":"plugin_section","embeddable":true,"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_section?post=308029"},{"taxonomy":"plugin_tags","embeddable":true,"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_tags?post=308029"},{"taxonomy":"plugin_category","embeddable":true,"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_category?post=308029"},{"taxonomy":"plugin_contributors","embeddable":true,"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_contributors?post=308029"},{"taxonomy":"plugin_business_model","embeddable":true,"href":"https:\/\/fy.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_business_model?post=308029"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}