Our API helps you to perform various tasks like summarization, language detection, sentiment analysis, article extraction, named entity recognition, extract text from various documents, images and audio files.
This endpoint is useful for extracting text from various documents types, images and audio files for further analysis.
Later on, you may choose to find important keywords or try to recognize various entities from the extracted text,
the applications are endless. This endpoint acts as an initial step for further text analysis.
file extension supported: csv, doc, docx, eml, epub, json, html, htm, msg, odt, pdf, pptx, ps, rtf, txt, xls, xlsx, gif, jpg, jpeg, png, tiff, tif, mp3, ogg, wav
max file input size: 10MB
max audio length: 60s (you can split audio files into smaller parts using ffmpeg)
supported languages: english