Three new text-to-speech voices are set to join the rSpeak Technologies family, for software development, cloud-based services, and server-based applications. The latest additions to the rSpeak voices lineup include Sophie (US English, female), Alice (British English, female) and Jack (Australian English, male), which join the already existing Jeff (US English, male), Max (German, male), Maja (Swedish, female), Ilse (Dutch, female), and Elise (French, female) voices.
rSpeak Technologies aims to provide developers with the tools to integrate fluent, natural text-to-speech voices and increase accessibility for all users. In the latest independent text-to-speech accuracy testing from ASRNews, rSpeak US English voice Sophie delivered exceptional results, including a first place for accuracy testing, among the overall field of leading text-to-speech developers. Testing by ASRNews covers more than 1,500 words and phrases, including acronyms, abbreviations, homographs, names, and numbers.
The addition of new voices to the rSpeak text-to-speech voice lineup adds to our robust set of text-to-speech tools for telephony systems, emergency management, public service announcements, public transport, connected devices, e-reading, e-learning platforms, and more. Text to speech improves the accessibility of these critical services for people with visual impairments, learning disabilities, literacy challenges, along with second-language learners as well as for enhanced usability for all. rSpeak Technologies believes that everyone deserves access to the same opportunities, and text to speech is an important tool in making that goal a reality.
rSpeak Technologies Chief System Architect Kåre Sjölander said : “We are committed to providing the best quality text-to-speech voices with a unique process for quality improvement. This process consists of extensive text normalization, dedicated coaching of voice talent, full quality assurance of the large amounts of recorded material focusing on the user experience, and a dedicated in-house prediction system that facilitates the speech enabling of words outside of our lexicon. This leads to amazing accuracy test results that validate our internal development efforts.”
rSpeak Technologies works with businesses, developers, OEMs and partners to provide embedded, server and cloud-based text-to-speech applications with different footprint levels. The rSpeak speech engine also powers popular e-learning platforms, allowing students to learn on their terms while increasing accessibility for segments of the population that aren’t sufficiently served by traditional, text-based content. The worldwide reach of mobile applications further underscores the need for audio interactivity, and rSpeak Technologies looks forward to seeing the creative ways in which developers integrate the latest additions to the rSpeak voices portfolio.