The voice interface for straightforward access to advanced voice technologies
SEMVOX.VI
TTS and ASR for any application
semvox.vi brings powerful embedded speech recognition (ASR) and text-to-speech (TTS) technology to your application.
It provides high-quality neural TTS as well as low footprint TTS in around 70 languages, optimized for announcements.
Embedded, fast automatic speech recognition (ASR) is available with both grammar-based support (including the ability to load dynamic data) and an embedded free-text recognizer. With semvox.vi, the ASR is both fast and reliable, making it perfectly suited for industrial applications.
semvox.vi is a versatile cross-platform software with ready-to-work audio integration for Linux, Windows, and Android. On top of that, its automation framework allows the easy configuration and execution of sub-dialogs.
TTS Features
With semvox.vi you have access to embedded neural TTS, multilingual voice and a wide variety of language and voices. Benefit from state-of-the-art TTS features like Emotional styles, SSML (pitch, rate, timbre etc.), or even create your own custom voice. We also offer low-footprint voices for efficient performance.
ASR Features
semvox.vi offers flexible recognition modes, supporting both grammar-based and free text inputs. It includes advanced features like dynamic vocabulary change or bage-in for natural interactions. Enhance accuracy with customizable dictionaries and benefit. We provide a wide language portfolio, and additional capabilities such as voice biometrics and sound identification are available on request.
REDEFINE THE STANDARD
Everything you need in one Interface
Your platform
semvox.vi runs on Windows, Android, Linux, and others on request
Your coding language
SDK available for Java, C#, C, and others on request
Your requirements
Choose a TTS or ASR technology that fits to your needs like low footprint or high-quality voice
Your solutions
semvox.vi is equipped with a built-in audio solution, with Bluetooth compatibility across most platforms
Your voice
Create a neural custom voice to make your product stand out
Your workflow
Reduce audio issues by using state-of-the-art voice technologies and use integrated tuning tools to fine-tune your use cases