SpeechKit Cloud is a Yandex cloud service that gives developers access to technologies for speech recognition, speech synthesis, and extracting semantic objects from spoken text. The infrastructure is designed for high loads to ensure availability and uptime, even with large volumes of concurrent requests. You can use the HTTP API to work with SpeechKit Cloud. This means you do not need to deploy and maintain your own infrastructure in order to quickly implement various features, such as:

  • Voice input in computer games and apps
  • Interactive voice response (IVR) menus in telephony
  • Spoken dictation for medical records of operations or other procedures
  • Voice interface for Smart Home systems
  • Voice interface for electronic robots
  • Voice control of home appliances, etc.
    • Supported languages for speech recognition:
        Russian (Queries, Maps, Dates, Names, Numbers, Music, Orders language models)
          English, Ukrainian, Turkish (Queries and Maps)
            German, French, Spanish (Maps model only)
              If your service doesn't work correctly with one of these models, please contact us via Feedback.
                Additional models available by request.
Getting started
  1. Read the terms of use.
  2. Send us an email to get an API key for your app.
  3. Review the documentation