By using Yandex Speech Synthesis (SS) plugin to UniMRCP Server, IVR platforms can utilize Yandex SpeechKit Text to Speech API via the industry-standard Media Resource Control Protocol (MRCP) version 1 and 2.
Yandex SpeechKit Text to Speech API performs text to speech conversion supporting the following main features.
Yandex SpeechKit composes speech from more than a million individual phonemes, with intonation set by a neural network trained on numerous real-life examples.
The text to speech API currently supports four languages.
The response time of API is so quick, that it allows for an efficient implementation of audio data streaming.
The text to speech API supports a variety of different male and female voices.
By using Yandex Speech Recognition (SR) plugin to UniMRCP Server, IVR platforms can utilize Yandex Cloud Speech to Text API via the industry-standard Media Resource Control Protocol (MRCP) version 1 and 2.
Yandex Speech to Text API performs speech transcription powered by machine learning and supporting the following main features.
Automatically transcribe audio in real-time using gRPC streaming.
The service infrastructure is designed with high loads in mind to ensure that the system is available and fault-free.
Numerous recognition models such as maps, dates, names and numbers are supported.
The speech recognition API currently supports two languages.