Market leading text to speech company CereProc adds Dutch to its range of commercially available synthetic voices in multiple languages. Full of character and emotion, the Dutch language TTS voice is available for download and deployment across multiple platforms using mobile channels, Windows, Mac OS X, CereVoice Cloud, SDK or cServer products.
An extension to the previous update to CereProc’s core synthesis engine, CereVoice - which included an advancement in platform compatibility, enhanced application stability and performance - the announcement of recently developed Dutch language marks a crucial stage in further expanding the text to speech company’s reach to new markets across Europe.
Confirming the speech technology company’s commitment to improved accessibility to materials for every individual - as set out last month with its call for improved accessibility to UK public services and resources - CereProc developed the Dutch language synthetic voice in partnership with
CereProc currently offers English in a number of region specific accents, French, German, Austrian, Italian and Spanish language synthetic voices for commercial download, while Romanian, Mandarin and Japanese languages are currently in beta phase.
ANIMATING VOCAL GAMING
Speech Graphics, the high-fidelity facial animation and lip synchronisation service, has received a £25k grant from the University of Abertay Prototype fund to develop facial animation technology for mobile devices.
The software will be integrated in games and apps to automatically animate the faces of 3D characters in precise synchrony with natural or synthetic voice.
While consumers are keen on high-fidelity devices, compelling facial animation is still missing from mobile apps. Using the Prototype funding, Speech Graphics that provide a voice-based animation service for game developers and other animators will bring its technology to iOS and Android devices, allowing developers to harness advanced speech processing and muscle-dynamic algorithms to animate speech and other facial behaviour realistically and with little effort.
Why use the voice-based service in game or animation project? Speech Graphics say quality and scalability as the service is audio-driven and 95% automatic, scaling to enormous volumes of lip synchronisation. Based on two decades of R&D in speech animation, reliable and controlled results with unprecedented quality are achievable.
Currently Speech Graphics clients provide their facial models and audio assets, and for the company to produce synchronised animation curves. with output provided in Maya or 3dsMax. The charge for animation at a simple per-second rate, plus a fee for each facial model setup. Rates vary, depending on volume.
(L2R) Michael Berger, co-founder and CTO of Speech Graphics says: “This development foretells awhole new way of interacting with mobile devices."
Co-founder and CEO Dr Gregor Hofer adds "We believe that in many ways the future will be in mobile. It is important as a supplier to stay ahead of the curve and making this R&D investment will cement our reputation in the industry as the leader in speech animation"