Ingestion Kit.
1 · Take inTurn anything your users upload into input your model can use. Your AI is only as good as what it reads. The Ingestion Kit makes every document, scan, web page and recording readable, so you ship answers instead of parsers.
75 APIs in this kitAPIs in the Ingestion Kit
75 servicesWorld News API
Search, extract, and retrieve news articles by URL, IDs, or source filters. Get titles, authors, summaries, publish dates, sentiment, and links.
SkycraftVerifiedConvert Speech to Text with (Whisper Large-v3)
Whisper Speech to Text transcribes speech in an audio file using OpenAI Whisper large-v3. Upload a WAV, MP3, M4A, or other common audio file as the file field of a multipart/form-data request, and the transcript comes back in a single synchronous call. There are no job IDs and no polling. The response is a small JSON object with three fields. text holds the transcript, or an empty string when no speech is found. language is the auto-detected language as an ISO 639-1 code, such as en. duration is the length of the input audio in seconds, which is useful for logging usage or checking what was processed. Use it for voice notes, call and meeting transcription, subtitle drafts, podcast and video indexing, voice-driven search, and any workflow that needs recorded speech as searchable text. Language detection is automatic, so you don't need to know the spoken language in advance. A file that can't be decoded as audio returns 400, and a request without a file field returns 422. Note: Runs OpenAI Whisper large-v3 (faster-whisper) on a dedicated NVIDIA RTX 5080 GPU. Response time scales with audio length: a few seconds for short clips and around 8 seconds for a one-minute recording.
MasterA AIVerifiedGameBrain API
Search games, fetch detailed metadata, find similar titles, and load game news. Useful for catalogs, recommendations, autocomplete, and editorial tools.
SkycraftVerifiedArt Search API
Search artworks by query, type, origin, material, technique, and date range. Retrieve artwork details or a random record with image, title, dates, and description.
SkycraftVerifiedDecode QR & Barcode API
Decode QR codes and barcodes from an image URL or base64 payload. Returns decoded text, format, position, and parsed payloads when available.
Callable LabsAI-ready Clean Data Extractor API
Clean Data Extractor: a web data extraction API that turns any URL into structured JSON with tables, links, headings and Markdown. Free tier, no card.
ApyHubVerifiedHosted on ApyHubExtract Sitemap from URL API
Extract URLs from a website's sitemaps, with optional sitemap metadata and async job polling. Built for SEO audits, crawl seeds, and inventory.
ApyHubVerifiedHosted on ApyHubConvert MP3 to AAC API
MP3 to AAC API: upload an MP3 or send its URL and get an AAC file back as a download or a signed link. For apps and podcasts. Free tier, no card.
ApyHubVerifiedHosted on ApyHubIngredient Parser From Text API
Ingredient parser API that turns a food label's ingredient text into the 14 EU allergens, E-number additives and vegan flags as JSON. Free tier, no card.
Fix PDF Orientation API
Auto-rotate misaligned PDF pages using OCR and track progress by job. Returns job IDs, status, progress, and the corrected PDF download.
FlowDocsVerifiedHosted on ApyHubExtract Website Contact Info API
Crawl a website and extract emails, phones, addresses, business names, named entities, and social profiles for lead enrichment and prospecting.
Dosvak LLCAdvanced Image OCR API
Extract text from an image with word-level bounding boxes, confidence scores, and a word count. Built for OCR pipelines, search, and archives.
Dosvak LLCWhich Ingestion API do you need?
The question you arrived with, and the API that answers it.
What is the Ingestion Kit?
The Ingestion Kit is the front door of your AI product. It takes the messy inputs real users send and returns clean text and structure your model, RAG pipeline or agent can work with.
It is the difference between a demo that works on one clean PDF and a product that works on everything your customers upload, from a scanned contract to a recorded call.
How AI products use it
- A legal AI reads contracts that users upload as scans or phone photos.
- A support copilot learns from help-center pages, PDFs and Word files.
- A meeting assistant turns call recordings into text it can summarize.
Why not build it in-house?
Each capability in the Ingestion Kit looks simple to build. The hard part is keeping it accurate, available and up to date once your product depends on it.
- OCRScans arrive skewed, low-resolution and in dozens of languages. Keeping accuracy up means tuning engines, retraining and testing on every new document type your users upload.
- PDF and table extractionEvery PDF generator writes files differently. Multi-column layouts, merged cells and embedded fonts break parsers, and each fix risks breaking another file.
- Web page to MarkdownWebsites change markup, add consent banners and block scrapers. A converter that worked last month quietly returns noise this month.
- Speech to textTranscription needs GPU capacity, model updates and handling for accents, noise and long recordings, all billed whether or not anyone calls it.
Do you run an API that belongs in the Ingestion Kit?
Publish it on ApyHub and put it in front of the teams and AI agents building with the Ingestion Kit. Your API joins the catalog under one subscription, becomes callable through MCP, and earns from every call.
Questions about the Ingestion Kit
What is the ApyHub Ingestion Kit?
The Ingestion Kit is the front door of your AI product. It takes the messy inputs real users send and returns clean text and structure your model, RAG pipeline or agent can work with.
What is a document parsing API?
A document parsing API takes a file such as a PDF, a scanned page or a Word document and returns its content as structured text, tables or Markdown, so software and language models can work with it.
How do I prepare PDFs and web pages for RAG?
Convert them to clean text or Markdown first. Use Extract Text from PDF for digital PDFs, the OCR APIs for scans and images, and Convert HTML to Markdown for web pages, then chunk and embed the result in your retrieval pipeline.
Which OCR API should I use?
AI Image OCR reads text from images and scans. Advanced Image OCR also returns word-level bounding boxes and confidence scores, which helps when you need to highlight or cite where text came from.
Can the Ingestion Kit transcribe audio and video?
Yes. Convert Speech to Text transcribes audio, AI Video Transcriber turns video into text, and AI Audio Language Detection tells you which language is spoken before you transcribe.
Can I test Ingestion Kit APIs before integrating them?
Yes. Every API has a Try it panel on its service page. Your key is filled in, you send a real request and see the actual response in your browser before you write any code.
Can AI agents use the Ingestion Kit?
Yes. Every endpoint is MCP-ready. Connect ApyHub MCP to Claude, ChatGPT, Cursor, Mistral Le Chat or any MCP-compatible agent, and your agent can discover and call these APIs directly.
How is it priced?
Every kit sits under one subscription, paid in atoms, ApyHub's usage unit. Every call shows its cost, and the free Starter plan needs no card.