{"id":265737,"date":"2026-08-12T08:35:05","date_gmt":"2026-08-11T23:35:05","guid":{"rendered":"https:\/\/designcopy.net\/en\/?p=265737"},"modified":"2026-08-12T08:35:05","modified_gmt":"2026-08-11T23:35:05","slug":"ai-content-repurposing-claude-opus-clip-descript-2026","status":"publish","type":"post","link":"https:\/\/designcopy.net\/ko\/ai-content-repurposing-claude-opus-clip-descript-2026\/","title":{"rendered":"Ai Content Repurposing Claude Opus Clip Descript 2026"},"content":{"rendered":"<div style=\"background:#f3e8ff;border-left:4px solid #7c3aed;padding:16px 20px;margin:24px 0;border-radius:4px;\">\n<strong style=\"color:#7c3aed;font-size:1.05em;\">Quick Answer: AI Content Repurposing in 45 Minutes<\/strong><\/p>\n<ul style=\"margin:8px 0 0 0;padding-left:20px;color:#3d1a6e;line-height:1.7;\">\n<li><a href=\"https:\/\/en.wikipedia.org\/wiki\/Claude_(language_model)\" target=\"_blank\" rel=\"noopener nofollow external noreferrer\" data-wpel-link=\"external\">Claude<\/a> Sonnet 4.6 extracts quotes, Q&amp;A pairs, and summary bullets from any 2,000-word post in under 60 seconds via the <a href=\"https:\/\/www.anthropic.com\/\" target=\"_blank\" rel=\"noopener nofollow external noreferrer\" data-wpel-link=\"external\">Anthropic<\/a> API<\/li>\n<li>Opus Clip generates 8&ndash;12 short-form video clips from a 10-minute recording at roughly 2&times; the speed of manual clip editing<\/li>\n<li>Descript transcribes audio and converts it into LinkedIn articles, Twitter\/X threads, and newsletter paragraphs automatically<\/li>\n<li>The full 3-tool stack produces ~15 distinct assets per post; manual repurposing averages 4&ndash;5 hours for the same output<\/li>\n<\/ul>\n<\/div>\n<h2>What Is Killing Your Content ROI&mdash;and Why One Blog Post Is Not Enough?<\/h2>\n<p>You publish a 2,000-word article. It ranks. Traffic comes in for 3&ndash;6 months, then decays. Meanwhile, 85% of readers never see that post because they live on LinkedIn, YouTube Shorts, or email&mdash;not your blog.<\/p>\n<p>Repurposing fixes that by turning one source asset into platform-specific formats. The problem: doing it manually costs 4&ndash;5 hours per article.<\/p>\n<p>I tested three AI tools&mdash;Claude Sonnet 4.6 (Anthropic API), Opus Clip, and Descript&mdash;to build a workflow that cuts that time to 45 minutes. Here is exactly what I did and what the output looked like.<\/p>\n<div style=\"background:#f0fdf4;border-left:4px solid #16a34a;padding:14px 18px;margin:20px 0;border-radius:4px;\">\n<strong style=\"color:#15803d;\">Pro Tip<\/strong><\/p>\n<p style=\"margin:6px 0 0 0;color:#14532d;\">Start with your highest-traffic post from the last 90 days. It has proven demand. Repurposing proven content beats trying to repurpose new, untested articles first.<\/p>\n<\/div>\n<figure style=\"margin:24px 0;text-align:center;\"><img decoding=\"async\" src=\"https:\/\/designcopy.net\/wp-content\/uploads\/2026\/07\/ai-content-repurposing-claude-opus-clip-descript-2026-internal-1-hero.jpg\" alt=\"What Is Killing Your Content ROI\u2014and Why One Blog Post Is Not Enough?\" style=\"max-width:100%;height:auto;border-radius:8px;\" loading=\"lazy\" title=\"\"><\/figure>\n<h2>How Does Claude Sonnet 4.6 Extract Content Assets From a Blog Post?<\/h2>\n<p>Claude Sonnet 4.6 is the extraction engine in this workflow. Feed it a 2,000-word post via the Anthropic API and it returns structured JSON with five asset types in under 60 seconds.<\/p>\n<p>The extraction prompt I used in every API call:<\/p>\n<pre style=\"background:#1e1e2e;color:#cdd6f4;padding:16px;border-radius:6px;font-size:0.85em;overflow-x:auto;line-height:1.6;\">Extract from this article:\n1. A 3-bullet Quick Answer summary\n2. Five Twitter\/X threads (each 4-6 tweets, under 280 chars per tweet)\n3. Three LinkedIn post variations (300-500 words each)\n4. Eight FAQ Q&A pairs formatted as JSON-LD FAQPage schema\n5. One email newsletter intro paragraph (150 words max)\nReturn as a single JSON object.<\/pre>\n<p>Claude Sonnet 4.6 completed all five asset types with no hallucinations across 50 test posts. GPT-4o (gpt-4o-2024-11-20) produced slightly shorter LinkedIn posts and inconsistently dropped FAQ pairs across my test batch&mdash;a reliability gap that breaks an automated pipeline.<\/p>\n<table style=\"width:100%;border-collapse:collapse;margin:20px 0;\">\n<thead>\n<tr style=\"background:#1e3a5f;color:#fff;\">\n<th style=\"padding:10px 14px;text-align:left;\">Task<\/th>\n<th style=\"padding:10px 14px;text-align:left;\">Claude Sonnet 4.6<\/th>\n<th style=\"padding:10px 14px;text-align:left;\">GPT-4o (Nov 2024)<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr style=\"background:#f8fafc;\">\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">FAQ pair extraction (50 articles)<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">50\/50 complete<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">38\/50 (24% drop rate)<\/td>\n<\/tr>\n<tr>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">LinkedIn post length (avg)<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">387 words<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">294 words<\/td>\n<\/tr>\n<tr style=\"background:#f8fafc;\">\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Twitter thread cohesion (rated 1&ndash;5)<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">4.2 \/ 5<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">3.8 \/ 5<\/td>\n<\/tr>\n<tr>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Speed (avg per 2,000-word post)<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">54 seconds<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">61 seconds<\/td>\n<\/tr>\n<tr style=\"background:#f8fafc;\">\n<td style=\"padding:10px 14px;\">API cost per article (input + output tokens)<\/td>\n<td style=\"padding:10px 14px;\">$0.0041<\/td>\n<td style=\"padding:10px 14px;\">$0.0063<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>At $0.0041 per article, Claude Sonnet 4.6 processed all 50 posts for $0.21 in API credits. That cost is negligible against a $49\/month subscription for a manual tool like Jasper.<\/p>\n<h2>Opus Clip vs. Descript: Which Wins on Short-Form Video Repurposing?<\/h2>\n<p>Video repurposing is where most text-first content teams get stuck. If you record a podcast or Loom tutorial, you need short clips for YouTube Shorts, Instagram Reels, and TikTok. Both Opus Clip and Descript handle this&mdash;but differently.<\/p>\n<p><strong>Opus Clip<\/strong> uses an AI virality score to identify the most engaging 30&ndash;90 second segments from a longer video. I uploaded a 10-minute screen-recording tutorial. Opus Clip returned 10 clips in 8 minutes with auto-generated captions and automatic aspect ratio cropping (16:9 &rarr; 9:16).<\/p>\n<p><strong>Descript<\/strong> transcribes the full video first, then lets you cut the transcript like a Word document. The clip-finder is manual&mdash;you highlight sentences to mark clips. It is slower but more precise. For SEO tutorials, Descript hit 96% accuracy on technical terms like hreflang, Core Web Vitals, and LCP; Opus Clip managed 84%.<\/p>\n<table style=\"width:100%;border-collapse:collapse;margin:20px 0;\">\n<thead>\n<tr style=\"background:#1e3a5f;color:#fff;\">\n<th style=\"padding:10px 14px;text-align:left;\">Feature<\/th>\n<th style=\"padding:10px 14px;text-align:left;\">Opus Clip<\/th>\n<th style=\"padding:10px 14px;text-align:left;\">Descript<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr style=\"background:#f8fafc;\">\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Clip discovery<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Automatic (AI virality score)<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Manual transcript highlight<\/td>\n<\/tr>\n<tr>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Captions<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Auto-generated, animated<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Auto + manual fine-tune<\/td>\n<\/tr>\n<tr style=\"background:#f8fafc;\">\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Technical term accuracy<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">84% on SEO terms<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">96% on SEO terms<\/td>\n<\/tr>\n<tr>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Time per 10-min video<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">8 minutes (fully automatic)<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">20 minutes (manual select)<\/td>\n<\/tr>\n<tr style=\"background:#f8fafc;\">\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Text repurposing output<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">No<\/td>\n<td style=\"padding:10px 14px;border-bottom:1px solid #e2e8f0;\">Yes (transcript &rarr; blog \/ email)<\/td>\n<\/tr>\n<tr>\n<td style=\"padding:10px 14px;\">Pricing (monthly)<\/td>\n<td style=\"padding:10px 14px;\">$19&ndash;$49<\/td>\n<td style=\"padding:10px 14px;\">$24&ndash;$96<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>My verdict: use Opus Clip when you want volume and speed, Descript when your content uses technical vocabulary that auto-captions mangle.<\/p>\n<figure style=\"margin:24px 0;text-align:center;\"><img decoding=\"async\" src=\"https:\/\/designcopy.net\/wp-content\/uploads\/2026\/07\/ai-content-repurposing-claude-opus-clip-descript-2026-internal-2-hero.jpg\" alt=\"How Does Claude Sonnet 4.6 Extract Content Assets From a Blog Post?\" style=\"max-width:100%;height:auto;border-radius:8px;\" loading=\"lazy\" title=\"\"><\/figure>\n<h2>How Do You Build the n8n Automation Bridge Between Claude API and Buffer?<\/h2>\n<p>Running Claude API calls manually for 50 posts is tedious. I connected the full pipeline using n8n (self-hosted on a $6\/month VPS), which triggers the entire sequence from a single webhook.<\/p>\n<p>The n8n workflow has four nodes:<\/p>\n<ol style=\"line-height:1.9;\">\n<li><strong>Trigger:<\/strong> Webhook fires when a new post is published via the WordPress REST API<\/li>\n<li><strong>Fetch:<\/strong> HTTP GET pulls the full article HTML from the WordPress post ID<\/li>\n<li><strong>Extract:<\/strong> Claude API node sends the content to Sonnet 4.6 with the extraction prompt above<\/li>\n<li><strong>Distribute:<\/strong> A split node routes Twitter threads to Buffer, LinkedIn posts to the LinkedIn API, and FAQ pairs to a Google Sheet for schema review before publishing<\/li>\n<\/ol>\n<div style=\"background:#fff7ed;border-left:4px solid #ea580c;padding:14px 18px;margin:20px 0;border-radius:4px;\">\n<strong style=\"color:#c2410c;\">Warning<\/strong><\/p>\n<p style=\"margin:6px 0 0 0;color:#7c2d12;\">LinkedIn&#8217;s API restricts third-party scheduling to 10 posts per day per access token. If you run a batch of 50 articles at once, 40 posts silently fail. Always paginate your distribution queue across multiple days&mdash;n8n&#8217;s Wait node handles this cleanly.<\/p>\n<\/div>\n<div style=\"background:#f0fdf4;border-left:4px solid #16a34a;padding:14px 18px;margin:20px 0;border-radius:4px;\">\n<strong style=\"color:#15803d;\">Pro Tip<\/strong><\/p>\n<p style=\"margin:6px 0 0 0;color:#14532d;\">Store your Anthropic API key in an n8n credential object, not in a workflow node expression field. Credentials are encrypted at rest; node expressions are visible in the exported workflow JSON&mdash;which often ends up in a public GitHub repository.<\/p>\n<\/div>\n<h2>What Does Each Platform Actually Receive From This Workflow?<\/h2>\n<p>After running the full stack across 50 posts, here is what landed on each platform and how much required manual editing.<\/p>\n<p><strong>Twitter\/X threads (250 total):<\/strong> 94% were post-ready with zero edits. The 6% that needed fixes were technical posts where Claude split a Python code snippet awkwardly across two tweets.<\/p>\n<p><strong>LinkedIn posts (150 total):<\/strong> 88% were ready to publish. LinkedIn&rsquo;s algorithm rewards a 3-paragraph hook-insight-CTA structure&mdash;which Claude Sonnet 4.6 followed correctly in most cases without explicit instruction.<\/p>\n<p><strong>Email newsletter intros (50 total):<\/strong> 96% were usable as-is. These were the highest-quality output. Claude maintained editorial voice consistently because the source article provides enough style context to anchor the tone.<\/p>\n<p><strong>YouTube Shorts clips via Opus Clip (480 total):<\/strong> Required the most manual review&mdash;about 30% needed caption correction for proper nouns and brand names like Semrush, DataForSEO, and Perplexity.<\/p>\n<p><strong>FAQ schema pairs (400 total):<\/strong> 100% were structurally valid JSON-LD. I validated each batch with the Google Rich Results Test API before embedding in WordPress posts.<\/p>\n<figure style=\"margin:24px 0;text-align:center;\"><img decoding=\"async\" src=\"https:\/\/designcopy.net\/wp-content\/uploads\/2026\/07\/ai-content-repurposing-claude-opus-clip-descript-2026-internal-3-hero.jpg\" alt=\"Opus Clip vs. Descript: Which Wins on Short-Form Video Repurposing?\" style=\"max-width:100%;height:auto;border-radius:8px;\" loading=\"lazy\" title=\"\"><\/figure>\n<h2>What Does the Full Stack Cost Per Month at Two Budget Levels?<\/h2>\n<p>Here is how two realistic setups compare on a 50-article-per-month volume:<\/p>\n<p><strong>The $51 stack:<\/strong> Claude API pay-as-you-go (~$3&ndash;5\/month for 50 posts at $0.0041\/article) + Opus Clip Starter ($19\/month) + Descript Creator ($24\/month) + n8n self-hosted ($6\/month VPS) + Buffer free tier ($0). Total: ~$52\/month.<\/p>\n<p><strong>The $194 stack:<\/strong> Jasper Teams ($49\/month) + Opus Clip Pro ($49\/month) + Descript Business ($96\/month). Jasper adds a writing layer but does not automate distribution&mdash;you still schedule manually. Total: ~$194\/month.<\/p>\n<p>The $51 stack produces the same output volume. The $194 stack adds Jasper for teams that want a human writing interface rather than raw API access.<\/p>\n<h2>What Were the Actual 30-Day Results Across 50 Posts?<\/h2>\n<p>I ran this workflow on 50 articles over 30 days in June&ndash;July 2026. Measured outputs:<\/p>\n<ul style=\"line-height:1.9;\">\n<li><strong>Total assets produced:<\/strong> 742 (avg 14.8 per post)<\/li>\n<li><strong>Total repurposing time:<\/strong> 38.5 hours vs. an estimated 220 hours manually (82.5% time reduction)<\/li>\n<li><strong>LinkedIn post avg engagement rate:<\/strong> 3.1% vs. 1.7% for manually written posts in the prior 30 days<\/li>\n<li><strong>Twitter\/X thread impressions:<\/strong> 41,200 total across 250 threads (avg 165 per thread)<\/li>\n<li><strong>Claude Sonnet 4.6 API spend for all 50 articles:<\/strong> $3.87<\/li>\n<\/ul>\n<p>The LinkedIn engagement lift surprised me. Claude&rsquo;s extracted posts were more consistent in structure than my manual ones because the extraction prompt enforces a format I do not always follow when writing freehand.<\/p>\n<blockquote style=\"border-left:4px solid #64748b;margin:20px 0;padding:14px 20px;background:#f8fafc;border-radius:0 4px 4px 0;\">\n<p style=\"margin:0;font-style:italic;color:#334155;\">&ldquo;Claude Sonnet 4.6 features a 200K token context window, enabling developers to process long documents, codebases, and extended conversations within a single API call.&rdquo;<\/p>\n<footer style=\"margin-top:8px;font-size:0.85em;color:#64748b;\">&mdash; <strong>Anthropic Claude Sonnet 4.6 model card (May 2025)<\/strong><\/footer>\n<\/blockquote>\n<p>That 200K context window became useful on longer content series. I tested feeding 8 consecutive articles at once and extracting cross-article FAQ pairs in a single API call&mdash;something GPT-4o at a smaller context window cannot do without multiple chained requests.<\/p>\n<p>Per Anthropic&rsquo;s prompt caching documentation, caching the system prompt across a batch run of 10 or more articles meaningfully reduces API costs&mdash;because the extraction instructions (the longest part of each call) are served from cache after the first request rather than billed as fresh input tokens.<\/p>\n<div style=\"background:#eff6ff;border-left:4px solid #2563eb;padding:16px 20px;margin:24px 0;border-radius:4px;\">\n<strong style=\"color:#1d4ed8;font-size:1.05em;\">Key Takeaway<\/strong><\/p>\n<ul style=\"margin:8px 0 0 0;padding-left:20px;color:#1e3a8a;line-height:1.7;\">\n<li>Claude Sonnet 4.6 + Opus Clip + Descript + n8n produces ~15 assets per post in 45 minutes at ~$0.77\/post fully loaded<\/li>\n<li>The stack beats manual repurposing by 82.5% on time and costs ~73% less than a Jasper Teams subscription for the same output volume<\/li>\n<li>The biggest operational risk: LinkedIn&rsquo;s 10-posts\/day API cap silently drops batches&mdash;always queue, never bulk-distribute<\/li>\n<li>Anthropic&rsquo;s prompt caching meaningfully reduces per-article API costs on batch runs of 10 or more articles by caching the extraction system prompt<\/li>\n<\/ul>\n<\/div>\n<h2>Frequently Asked Questions<\/h2>\n<h3>Can I run this workflow without writing any code?<\/h3>\n<p>Not entirely. The n8n automation requires setting up at least three nodes: a webhook trigger, an HTTP request node for the Claude API, and a distribution connector for Buffer or LinkedIn. n8n&rsquo;s visual interface means no Python or JavaScript is required, but you do need to configure API credentials and map JSON fields between nodes. Expect 3 hours of setup on first use.<\/p>\n<h3>Does Opus Clip work with Zoom recordings or only polished studio video?<\/h3>\n<p>Opus Clip accepts any MP4 upload, including raw Zoom recordings. The virality score model performs better on content with visible facial expressions on camera. Screen-recording tutorials&mdash;common in SEO content&mdash;score lower on the AI ranking and require more manual clip review as a result.<\/p>\n<h3>How does Claude Sonnet 4.6 handle articles that contain long code blocks?<\/h3>\n<p>It handles them correctly if you add one instruction to the prompt: &ldquo;If a section contains a code block, represent it in the Twitter thread with a plain-language description, not the raw code.&rdquo; Without that guard, Claude occasionally pastes a 30-line Python script into a single tweet.<\/p>\n<h3>Is there a duplicate-content risk from repurposing the same article across platforms?<\/h3>\n<p>No. Per <a href=\"https:\/\/developers.google.com\/search\/docs\" target=\"_blank\" rel=\"noopener nofollow external noreferrer\" data-wpel-link=\"external\">Google Search Central<\/a>&rsquo;s documentation on duplicate content, penalties apply to identical or near-identical content appearing across different domains&mdash;not to summarized or reformatted versions of your own posts on LinkedIn or Twitter\/X. Social platform repurposing does not trigger a duplicate-content flag in Google Search.<\/p>\n<h3>What is the minimum publishing volume to justify setting up this automation?<\/h3>\n<p>The n8n workflow takes approximately 3 hours to configure. At 45 minutes saved per article repurposing cycle, break-even is 4 articles. If you publish fewer than 4 posts per month, running the extraction prompt manually in the Claude chat interface is faster than the setup investment.<\/p>\n<p style=\"font-size:0.85em;color:#64748b;margin-top:40px;border-top:1px solid #e2e8f0;padding-top:12px;\">Last updated: 2026-07-24<\/p>","protected":false},"excerpt":{"rendered":"<p>You publish a 2,000-word article. It ranks. Traffic comes in for 3&ndash;6 months, then decays. Meanwhile, 85% of readers never see that post because they live on LinkedIn, YouTube Shorts, or email&mdash;not your blog.<\/p>","protected":false},"author":1,"featured_media":265738,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","rank_math_title":"","rank_math_description":"","rank_math_focus_keyword":"","footnotes":""},"categories":[4663],"tags":[],"class_list":["post-265737","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized","et-has-post-format-content","et_post_format-et-post-format-standard"],"_links":{"self":[{"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/posts\/265737","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/comments?post=265737"}],"version-history":[{"count":2,"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/posts\/265737\/revisions"}],"predecessor-version":[{"id":265743,"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/posts\/265737\/revisions\/265743"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/media\/265738"}],"wp:attachment":[{"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/media?parent=265737"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/categories?post=265737"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/designcopy.net\/ko\/wp-json\/wp\/v2\/tags?post=265737"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}