Give your next training video a different feel by using IBM Watson Text to Speech. The tool enables users to convert text into natural, human-sounding speech for applications such as voice-automated chatbots, voice-driven and screenless applications for people with disabilities or visual impairments, and, of course, narration and voice-overs for training videos.
IBM's Lite plan is free and allows up to 10,000 characters per month at no cost. Get started by following the instructions to create an audio file with your text. Text to Speech offers a variety of languages, including Arabic, Chinese, Dutch, Hindi, and Portuguese. The service provides voices with man- and woman-sounding tones for each language.
Text to Speech's voices use neural voice technology, which produces human-sounding speech patterns. The two voice types are expressive neural and enhanced neural, which have different qualities and capabilities. Expressive neural is more conversational and is available in Australian English and US English. Enhanced is available in all languages except Australian English.
Additional features include the ability to refine pronunciation by defining words with foreign origins, proper names, and abbreviations or acronyms.
