TextRazor uses state-of-the-art Natural Language Processing and Artificial Intelligence techniques to parse, analyze and extract semantic metadata from your content.

Our high performance machine learning stack was designed from the ground up for accuracy, speed and robustness across varied styles of writing.

Integrate in minutes

TextRazor's API can be easily integrated with any language that can send an HTTP request and parse the JSON response, making powerful text analytics possible with only a few lines of code. TextRazor allows you to extract any and all the information you need in one request, linking the extracted semantic metadata to make identifying complex patterns easy.

Uncompromising Latency, Throughput and Big Scalability

Big Data is only useful if your software can keep up with it. TextRazor was designed from the ground up for performance. Written in heavily optimized C++, TextRazor is capable of processing thousands of words per second per core. Our distributed backend processes tens of millions of documents per day for hundreds of clients.

TextRazor's resilient infrastructure is built on the Amazon Web Services cloud and physical hardware. TextRazor is designed for high availability and performance consistency for the analysis of thousands, millions or billions of daily documents.

Daily Updates

Language is always changing - our models are updated with new entities on a daily basis, so you will never miss anything important. We also completely rebuild our models from scratch every month to pick up larger shifts in language use.

Limitless Customization

TextRazor allows you to add Product Names, People, Companies, custom classification rules and advanced linguistic patterns. Our integrated Prolog engine lets you rapidly combine TextRazor results with robust custom domain specific logic.

You can read more about our rules engine here.

% Match two companies in a 'buy' relation.
acquisition_rumor(CompanyA, CompanyB, EntailedWord) :-
    entity_type(CompanyA, 'Company'),
    entity_type(CompanyB, 'Company'),
    relation_overlap(BuyRelation, 'SUBJECT', CompanyA, 'OBJECT', CompanyB),
    entailment_overlap(_, BuyRelation, EntailedWord),
    member(EntailedWord, ['buy', 'sell', 'acquire']).

Find out more

TextRazor is built from a number of integrated modules for performing various extraction tasks, find out more about each in particular using the links on the left. If you've any specific questions, or are interested in how we can make our technology work for you, we'd love to talk further.