Contact us

A new window will open A new window will open

Text-To-Speech Middleware

Toshiba Text-To-Speech Middleware is a software IP that enables smooth and natural reading of text data while running on the CPU and memory of a local device.

Features

Smooth reading
  • Using a proprietary technology, Toshiba Text-To-Speech Middleware delivers smooth and natural speech with uniformly high sound quality.
Clear and natural sound quality even with small memory footprint
  • Clear sound quality is kept enough even with only a few megabytes of memory for the synthesis unit dictionary (voice database).
Small computational cost
  • With its compact size, Toshiba Text-To-Speech Middleware can work in real-time even when run on local terminals. In this case it eliminates the problem of network delay, which is unavoidable with cloud solutions.

This figure shows the features of Toshiba Text-To-Speech Middleware about sound quality and memory size.

The comparisons between Toshiba Text-To-Speech Middleware and the Conventional Speech Synthesis Technology

Product Lineup

Product Lineup

TSPG1 TSPG2 TSPG3
Standard Voice Synthesis
Optional Voice Synthesis (Japanese) -
Phonetic Symbol Entry
Embedded Tags -
Lexicon Small Small Large
ROM/RAM (Typ.) 4.3 MB/2.0 MB 4.8 MB/5.3 MB 12.9 MB/5.8 MB
MIPS (Typ.) 65 75 110 to140
Language Japanese, three main languages in North America(English, French, Spanish), Chinese Japanese Japanese
Support of other languages is being planned.

*The ROM/RAM requirements and the MIPS values are provided as a guide for the Japanese edition of the minimum middleware configuration. They vary depending on the platform, middleware configuration and its setup.

Two Configurations

Select the best configuration for your application.

Features of the SYN Configuration
  • Takes a string of phonetic symbols as input and adds natural prosody and intonation
  • Eliminates the need for linguistic dictionary and thus saves memory.

This figure shows the features of the SYN configuration.

Features of the TTS Configuration
  • Accepts plain text as input and converts it into speech.
  • Supports phonetic transcriptions as input.

This figure shows the features of the TTS configuration.

Benefits of Using Speech Synthesis

Click this image to hear a sample voice.

Route guidance of a car navigation system

Text-To-Speech middleware enables route guidance including a huge number of proper nouns with a natural-sounding voice. Spoken contents can be upgraded through simple maintenance of a phonetics database; it is unnecessary to record utterances spoken by professional narrators.

 

Drive assist

Draws a driver's attention with voice warnings.

 

Hands-free phone calls

You know who is calling without taking your eyes off the road.

 

Reading out the delivered information

You can make Text-To-Speech middleware read out content delivered from information service providers.

 

Reading out emails

Why not add voice messages to make your emails friendlier?

 

Other Language Samples

Japanese

 

Chinese(Mandarin)

 

* System and product names mentioned herein may be trademarks or registered trademarks of respective companies or organizations.

Contacts

If you have any questions, click one of these links:

Technical queries
Questions about purchasing, sampling and IC reliability
To Top
·Before creating and producing designs and using, customers must also refer to and comply with the latest versions of all relevant TOSHIBA information and the instructions for the application that Product will be used with or for.