semvox TTS

 

A new generation of text-to-speech solutions

semvox Text-to-Speech (TTS)

is a suite of speech output solutions to generate high-quality speech, with seamless blending of dynamic text-to-speech, pre-recorded audio, and tuned prompts. The technology is optimized to read long texts in a natural, human way. New deep learning based algorithms deliver higher smoothness and more natural prosody, resulting in a unique voice experience.

Public Address (PA) and Announcement Solutions: Synthetic Voices (Text-to-Speech)

Voice solutions are a proven technology around the world in numerous applications as passenger information, ticketing machines, flight announcement and customer guidance systems in public buildings.

A high-quality Text-to-Speech (TTS) with a pleasant, intelligible and familiar voice and providing precise and up-to-date information, helping passengers feel more comfortable. Thus, increasing customer satisfaction and information efficiency.

The semvox Text-to-Speech engine enables you to enrich your passenger information systems via a digital //or synthetic voice that is both flexible and of high quality.

New flyer available!

Download now the latest pdf-flyer about semvox.vi for announcement systems:

 

AVAILABLE LANGUAGES

semvox offers a truly universal voice portfolio that comes with more than 64 languages and 141 voices for the creation of global solutions using a single engine. The language and voice portfolio is continually expanding.

Your desired language is not listed? Contact us!

A

_Arabic Gulf & Levantine

B

_Basque

_Bengali

_Bhojpuri

_Bulgarian

C

_Cantonese

_Catalan

_Croatian

_Czech

D

_Danish

_Dongbei

_Dutch

\_Belgian DUT

\_Netherlands DUT

E

_English

\_Australian ENG

\_British ENG

\_Indian ENG

\_Irish ENG

\_Scottish ENG

\_South African ENG

\_US ENG

F

_Farsi

_Finnish

_French

\_Canadian FRE

\_France FRE

G

_Galician

_German

_Greek

H

_Hebrew

_Hindi

_Hungarian

I

_Indonesian

_Italian

J

_Japanese

K

_Kannada

_Korean

M

_Malay

_Mandarin

_Marathi

_Mexican

N

_Norwegian

P

_Polish

_Portuguese

\_Brazilian POR

\_Portuguese POR

R

_Romanian

_Russian

S

_Shaanxi

_Shanghainese

_Sichuanese

_Slovak

_Slovenian

…

…S

_Spanish

\_Argentinian SPA

\_Chilenian SPA

\_Colombian SPA

\_Spain SPA

_ Swedish

T

_Taiwanese

_Tamil

_Telugu

_Thai

_Turkish

U

_Ukrainian

V

_Valencian

_Vietnamese

 

Text to Speech: On premise or as a service?

No matter if your application requires an embedded on-premise or Cloud-as-a-Service Text-to-Speech solution: Our technology adapts your requirements.

TECHNICAL FEATURES AND ASPECTS

  • Emotional TTS

Developers can choose from 4 different speaking styles: neutral, lively, forceful, and empathic

  • Gilded speechdatabases

Speaking styles are enhanced by selecting expressive pre- recorded prompts (incl. nonverbal) from a “gilded speech” database accompanying the TTS voice

  • New timbre markup tag controls the perceived

age, gender, or physical size of a TTS voice

  • Multi-lingual support

Automatic language identification, foreign language dictionaries, and high-quality acoustic extensions provide unparalleled multi-lingual readout

  • Seamless prompt insertion

Recorded audio prompts or tuned prompts are seamlessly blended with dynamic text-to-speech using automatic text matching (active prompt mechanism)

  • Offline Audio Generation
  • Free Audio Path Design
  • Prosody control

Volume, pitch, speaking rate, and timbre can be changed at run time for more dynamic and lively effects

  • Phonetic input

Optimize quality using phonetic information from an external contents source like music or map data

  • User text rules

Write regular expressions to expand custom abbreviations and text patterns

  • User dictionaries

Create your own dictionaries for out-of-vocabulary Words

  • Prompt sculpting

Change unit selection results manually to increase expressibility and remove glitches

  • SSML support
    Speech Synthesis Markup Language (SSML) allows for TTS vendor-independent markup
  • SAPI support
    Operate the TTS Engine over the Windows Speech Application Programming Interface.

SUPPORTED PLATFORMS

PC and Server Platforms

Windows: 32-bit and 64-bit

Linux x86: 32-bit and 64-bit

OS X: 32-bit and 64-bit, Intel only, OSX 10.9+, Xcode 6.0+

Mobile Devices

Linux ARM: ARM32 Hardfp, ARM32 Softfp, ARM64

Android v4.0: API level 14+, ARM32-v7a

Android v7.0: API level 24+, ARM64-v8a

iOS

powered by:

Please contact us for a non-binding consultation and learn more about the possibilities and advantages of the Cerence technologies for your products and applications.