We have developed a ready-made speech synthesis service that can be deployed as part of our own software in any business area where customer needs voice assistant in addition to self-service systems.
For the creation of sound files any speech recognition and voice service can be used — Google Text-to-Speech, Yandex SpeechKit, Microsoft voice platform. At this stage, our service relies on a solution from Google, we are ready to connect other voice platforms at the customers request.
Key features of the Google Text-to-Speech platform, that we use:
Support for 120+ languages and linguistic varieties
Accurate pronunciation, formatting of phrases depending on the language situation (for example, date, phone numbers)
High level of speech imitation, close to real human voice
Support for Speech Synthesis Markup Language (XML based)
The service is already used in our Queue management system, it presents a simple and powerful API that allows to receive mp3 voice messages generated on the basis of a third-party voice platform at real-time or pre-create cache from sound files. The cache is built on the basis of our own algorithms and the internal base of the service.
Advantages of our solution:
Low cost of new files generation. For the base of sound files based on Google Speech-to-Text price is 16 USD for 1 million characters
Decrease in ownership cost of the service due to message segmentation. Each unique segment is voiced only once
For an average electronic queue, about 200 USD is enough for a seamless (without segmentation) voicing of all texts scenarios for client invitation
Our own message normalization algorithms that further reduce requests to external services
Modern voice services at a relatively high level solve the problem of simulating pronunciation, close to natural — eliminated the problems of recreating the smooth sound and intonation.
The solution that we created uses all the advantages of modern voice recognition and sound technologies from the world's largest developers. If necessary, we are ready to provide our existing or potential customers with voice assistant system for any software product, with the shortest launch time and minimal financial costs.