TextTeaser, the text-summarization API that TechCrunch first profiled back in October 2013, is now open source and available on GitHub. Creator Jolo Balbin says that he decided to make the code available after “stumbling upon some scalability issues, especially in the API.”
So he took down the API and recoded TextTeaser to make its auto-summarization process faster. Developers can chose from two plans, including one that costs $12 for every 1,000 articles summarized. The second is an enterprise plan that costs $250 per month and comes with a dedicated server that can store the article source. That means each time someone uses the tool to summarize an article, TextTeaser will learn the keywords in the text and use it to improve its results.
“In this TextTeaser, you can train your own summarizer,” Balbin explains. “You can provide the category and source of the article that will be used to improve the quality of the summaries. In the future, users might also have the ability to provide what keyword is important and what is not.”
Developers have integrated TextTeaser with news reader apps, including Gist. Balbin is also planning to optimize it for financial, medical and legal documents, which are often very long and onerous to read.