The Microsoft Azure Cognitive Services Speech Services API enables real-time transcription of audio streams into text. It allows your applications, tools, or devices to consume, display, and take action on, command input to the Speech-to-text service. This service is powered by the recognition technology that is used for Cortana and Office, and works with the translation and text-to-speech services as well. Requests to the Speech Services API can only contain 10 seconds of recorded audio and returns final results, as partial results are not supported. It provides a way to capture audio from a microphone, read from a stream, and more. Azure supports reinforcement learning, a set of techniques that performs artificial intelligence optimization based on your configuration. It allows you to integrate cloud services to develop, test, deploy, and manage applications, and utilize the efficiencies of cloud computing. Azure is a complete cloud platform to host your existing applications, streamline the development of new applications, and enhance on-premises applications.
The following is a list of SDKs from our SDK directory that matched your search term. Though your definition of an SDK may differ, in our world, we define SDKs as platform- specific tools for consuming existing APIs of the sort we list in our API directory. For example, the Ruby SDK for consuming the Twitter Ads API. If you think an SDK, API, or other asset is missing from our directory, be sure to check our guidelines for making contributions to ProgrammableWeb.
The Microsoft Azure Cognitive Services Swift SDK by Vladimir Danila interacts with the API to access image analysis and character recognition services. Developers can preview the interaction with the APIs that include Computer Vision API, Emotion API, Face API, Video API, Speaker Recognition API, Speech API, Linguistic Analysis API, Web Model Analysis API, and Entity Linking API.