For good or bad many sites are now using CAPTCHAs to determine if visitor is human or computer program. Captcha presents a task – usually reading some distorted letters  and writing them back to a form.  This is considered to be hard for computer to do, so user must be human.  To improve accessibility visual captchas are accompanied by audio captchas, where letters are spelled (usually with some background noise to make letters recognition more difficult) .  However audio captchas are know to be easier to break.  Inspired by this article [1]  I created a python implementation of audio captchas decoding using commonly available libraries and with just a general knowledge of speech recognition  technologies. Software is called adecaptcha and I tested it on couple of sites, where I got 99.5% accuracy of decoded letters for one site and 90% accuracy for other site (which has much distorted audio). Continue reading Decoding Audio Captchas in Python →