Skip to main content

Who we help

GistCite for developers and AI builders

Every tool in the web app is one REST call with the same account and quota: transcripts, documents with page anchors, chunked JSON for vector stores, web extraction and Whisper.

Published · Reviewed

What you can do with it

Document Extractor

Ingest documents into a RAG pipeline

Chunked JSON with page, section and character offsets, from one endpoint.

How Document Extractor does it

Web Extractor

Web pages as clean Markdown

Fetch or browser-render, with optional CSS-selector schemas for structured output.

How Web Extractor does it

The tools you will use most

  • Document Extractor

    Extract clean text and LLM-ready Markdown from PDF, DOCX, PPTX, XLSX, TXT, EPUB and HTML, with OCR for scans, then export in nine formats.

  • YouTube Transcripts

    Paste a YouTube link and get the full transcript with timestamps, in the video's own language or translated, as text or SRT subtitles.

  • Web Extractor

    Extract public web pages into clean Markdown, text, HTML, JSON or structured fields, in batches of 25 or crawls of up to 200 pages, with browser rendering.

  • Speech to Text

    Dictate live in the browser for free, or upload a recording up to 500 MB for a Whisper transcript with word timestamps and SRT export.

  • AI Summary, Ask and Create

    Summarize any source into an overview, key points and timestamped chapters; ask questions with citations; create posts, briefs and scripts from it.

Worked examples

Graduate student

From a twelve-lecture playlist and two textbooks to a searchable study corpus

A public lecture playlist and two public-domain textbooks become one set of transcripts, summaries and chunked JSON, ready for revision or a personal AI index.

Follow the walkthrough

Questions from this audience

How do I authenticate?
Mint an API key on the Account page and send it as a Bearer token or X-API-Key header. Keys are shown once and stored hashed.
What does a call cost?
The same units as the web app: 1 for an extraction, 10 or 30 for an AI action. Every metered response carries X-Quota headers.

Further reading

Try it on your own material

The free plan covers transcripts and document extraction; Pro adds the AI and media tools.