Speech can be synthesized for an audio message to the calling and/or receiving subscriber directly during the call. This requires specifying the text for synthesis, selecting a voice from 13 available options, intonation, and speed of text pronunciation. After that, when the subscriber accepts the call, the synthesized message will be played to them before being directly connected to the interlocutor.
For example, in the case of a callback request from the website "Call me back," the client will hear the message "Connecting you to an operator, all calls are recorded," and the operator will hear "Connecting you to a call from the website." And when sending a voice SMS, a personalized message can be sent with a greeting to the client by name.
Vasily Sazhko, Director of Products at MTS Exolve, said:
The advantage of on-the-fly speech synthesis is that to launch an auto-dialer or callback, you no longer need to pre-record or synthesize an audio file, add it to the account library, and transmit its identifier during the call. This approach will provide businesses with more flexible, faster, and more efficient communication with customers. This is especially useful when voicing content with variables, individual user requests, or the need to frequently update information in real time, such as changes in departure times at the airport.