RealSpeak™ Solo is a text-to-speech solution, optimized to enhance embedded conversational applications. It is a scalable solution that provides exceptionally high speech quality output across a range of footprints. Scaling from 8 to 20MB for embedded and automotive applications and up to 100MB for desktop applications, it is the ideal solution for a wide range of deployments where high quality speech output is essential.
Thanks to its unrivaled voice and language portfolio, and its availability at several memory footprint options, RealSpeak Solo 4.0 is uniquely able to serve a huge range of deployments and application areas, including:
Automotive Manufacturers
Device Makers
Telematics Suppliers
Banks
Kiosk Developers
Electronic Game Creators
Custom Voice Program
Even more exciting, it is now possible for you to have your choice of voice captured at this unique quality level on RealSpeak Solo 4.0. Pick your preferred speaker, tell us your brand requirements for the sound and feel of your applications, and Nuance will quickly deliver the tailored TTS voice that allows you to drive your brand across your entire range of voice services. Nuance has a streamlined, repeatable process, and a proven track record of delivering voices that truly capture the qualities of any speaker. Nuance offers the full range of custom voices from general purpose voices to domain optimized voices with human-like quality in their target application domain.
System Requirements
Windows Requirements
Intel Pentium-based PC (266 MHz) or higher
64Mb RAM
SoundBlaster 16-compatible audio device
Windows 98, Windows Me, Windows NT 4.0, Windows 2000, or Windows XP
WinCE Requirements
Microsoft Embedded Visual C++ 3.0 or later
Pocket PC 2003
Arm Compatible Processor (Strong Arm, Xscale, S3C2410)
WinCE Version 3.0 or later
The full speechbase versions are not included in WinCE.
Memory Requirements
Required Disk Space (Average)
Frequency vs. Footprint
Small Reduction
Medium Reduction
Full Speechbase
11 kHz
8 MB
12 MB
30-40 MB
16 kHz
10 MB
16 MB
--
22 kHz
12 MB
20 MB
> 60 MB
Required RAM Memory Usage (Average)
Frequency vs. Footprint
Small Reduction
Medium Reduction
Full Speechbase
11 kHz
4 MB
4.5 MB
8 MB
16 kHz
4 MB
4.5 MB
--
22 kHz
--
--
8 MB
The values in the table represents average values. There can be size differences depending on the specific voice used.