Skip to content

Developer docs

Turn anything into text — from your code.

Textify exposes the same engines that power the website as a metered REST API and a hosted MCP server — so your apps and AI agents can transcribe, OCR, and convert without shipping any models.

API https://api.textify.me  ·  MCP https://mcp.textify.me/mcp

What you can do

YouTube transcripts

Pull the caption track from any public video — captions only, never the media.

Transcribe audio & video

Cloud speech-to-text over a URL or upload, with timestamped segments.

OCR images

Read text out of photos, screenshots, receipts, and handwriting.

Web page → Markdown

Fetch a page, strip the clutter, get clean Markdown (SSRF-guarded).

Files → text / Markdown

PDFs, Word/PowerPoint/Excel, and EPUB — scanned pages fall back to OCR.

Free tier & pricing

Every account gets 100 free credits every month — no card required. Metered work spends credits from your balance; most requests cost a single credit. When you need more, credits are $5 per 1,000, and the Pro plan includes 2,000 credits a month.

Honest pricing

You only pay for the handful of jobs a browser genuinely can't do. In-browser conversion on textify.me is free and unlimited, and your TXT/SRT/VTT exports are never paywalled. See the full pricing page for plans and packs.

Endpoints & credit costs

Five endpoints, one auth scheme, one balance. Credit costs below are read from the shared credit schedule at build time, so they always match what you're actually billed.

Endpoint What it does Cost
POST /v1/youtube/transcript Fetch a YouTube transcript 1 credit per video
POST /v1/transcribe Transcribe an audio or video URL 15 credits per audio-hour
POST /v1/ocr Read text out of an image 1 credit per image or page
POST /v1/web/markdown Convert a web page to Markdown 1 credit per fetch
POST /v1/convert Convert a document to text or Markdown 1 credit per fetch

Credit schedule

Action Credits Billed
YouTube transcript (captions) 1 per video
YouTube transcript (AI fallback, caption-less) 3 per video
Cloud transcription 15 per audio-hour
OCR / handwriting 1 per image or page
Web page → Markdown 1 per fetch

Start building