Fewer than 100 lines of code for an initial recognition and synthesis application.

Fully configurable at the same time.

» Simple integration of speech technologies

» ASR & TTS offline and embedded on your device

» Generic interface to various TTS and ASR suppliers

» Runs on various systems: Linux, Windows, Android, others*

» Native and efficient implementation in C

» SDK available for Java, C#, C, others*

» Easier entry through code samples and sample apps

» Simplified dialog management via automation-framework

» Touchpoint to geni:OS - Access to semvox technologies enables the implementation of intelligent assistance systems

Text-To-Speech (TTS)

» 65 languages

» 152 voices (male/female)

» Multilingual

» Plain text or SSML

» Emotional TTS*

»  Custom Voice

» Multiple instances in parallel

» TTS Service for Android

Automatic Speech Recognition (ASR)

» Wake-up word

» Barge-In

» Grammar-based recognition

» Recognition of dynamic slots

» Embedded free text recognition*

» Voice biometrics*

» Sound identification*

» Low latency speech recognition

Use Case Examples

Keyword Recognition

System:
“Which restaurant do you want me to find
for you?”

Nutzer:
“Hmm, I feel like Chinese today”

Multilingual Speech Models

User:
“Play ‚Clair de Lune‘ by Claude Debussy”