The content engine, over HTTP.
Whizz Scribe is a REST API that researches, writes, scores, and publishes blog articles grounded in your company's knowledge base — with real citations, SEO metadata, and one-call CMS publishing. You send a topic; the engine does the rest.
What the API does#
One POST /v1/articles call runs a multi-stage pipeline: it studies what currently ranks for your keyword, plans an angle with genuine information gain, researches the web and your private knowledge base in parallel, drafts, runs an editorial pass that strips AI-tell phrasing, finishes SEO (meta tags, FAQ schema, JSON-LD, A/B title variants), and scores the result on a 0–100 quality rubric. Optional add-ons generate a hero image and platform-native derivatives (X thread, LinkedIn post, newsletter).
Articles are grounded in brand profiles: crawl your website or upload writing samples, and the engine extracts a fact sheet plus a portable voice profile that every article follows.
The async job model#
Article generation takes minutes, not milliseconds, so the API is asynchronous. Creation returns 202 Accepted with a job ID immediately; you poll the job or receive a webhook when it finishes.
POST /v1/articles
Returns 202 with a job object. Credits are debited up front and auto-refunded if the job fails.
{ "id": "…", "object": "job", "status": "queued" }
Pipeline runs
recon → plan → research → draft → edit → seo → score (+ image, derivatives when requested). Each stage is reported live on the job.
Poll GET /v1/jobs/{id} — or receive a job.succeeded webhook
job.status moves queued → processing → succeeded | failed. On success, result.article_id points at the finished article.
GET /v1/articles/{id}
Full article: markdown + HTML, citations, SEO metadata, FAQ, JSON-LD, quality breakdown, derivatives.
then POST /v1/articles/{id}/publish to WordPress, Sanity, or Contentful
Base URL#
https://scribe.whizztech.ai/v1All endpoints live under /v1 and speak JSON over HTTPS. Responses carry rate-limit headers on every call.
Authentication at a glance#
Every request is authenticated with an API key in the Authorization header. Keys are created in the dashboard and start with wz_live_ or wz_test_:
curl https://scribe.whizztech.ai/v1/usage \
-H "Authorization: Bearer wz_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"Details — key format, storage, and failure shapes — are on the Authentication page.
OpenAPI spec#
The whole surface is described in a machine-readable OpenAPI 3.1 document — usable for codegen, Postman imports, or contract tests: download the spec or browse it at /openapi.json.