Speech Resources

Leading speech engines run over IVR or IVVR platforms


Text-to-Speech (TTS)

Vxi runs most Text-to-Speech (TTS) engine thru an advanced, universal HTTP open source interface or MRCP that helps developers manage multi-vendor TTS engines in the same or different server(s).

Speech Recognition (ASR)

Vxi runs several speech recognition (ASR) connectors for Asterisk speech API or MRCP v1 and v2 through uniMRCP. You can develop advanced speech enabled dialogs in VoiceXML.

Natural Language (NLU)

Natural Language Understanding (NLU) core technology behind our IVR solutions. NLU enables smarter and more efficient applications that can quickly route calls and enhance the customer experience throughout the entire human like conversational self-service engagement. Vxi is compatible with several leading NLU standard based engines.

Voice Biometrics (SIV)

Voice biometrics is the technology behind voice (or speaker) verification (SIV), which in turn is an application of the core technology. The voice, as with other biometric characteristics, is unique to an individual. In voice biometrics, a spoken utterance is captured by IVR and compared by the biometric system with a previously stored voiceprint. Vxi is compatible with most voice biometrics APIs in the market.

Speech-to-Text (STT)

Speech to text conversion is the process of converting spoken words into written texts. Vxi supports many Speech-to-Text engines to convert any voice recording into text. Vxi is compatible with many STT engines and can works with many others.

Text-to-Video (TTV)

Vxi runs a Text-to-Video (TTV) extended feature for video services enabling to generate a real-time video content from a text in order to print a message or dynamic menu on your video phone screen. TTV is an internal feature of Vxi.