What is a voice assistant?
By using voice assistants with the Speech service, developers can create natural, human-like, conversational interfaces for their applications and experiences. The voice assistant service provides fast, reliable interaction between a device and an assistant implementation.
Choose an assistant solution
The first step in creating a voice assistant is to decide what you want it to do. Speech service provides multiple, complementary solutions for crafting assistant interactions. You might want your application to support an open-ended conversation with phrases such as "I need to go to Seattle" or "What kind of pizza can I order?"
Reference architecture for building a voice assistant by using the Speech SDK
Core features
When you choose Custom Commands to create your assistant interactions, you can use a rich set of customization features to customize your assistant to your brand, product, and personality.
| Category | Features |
|---|---|
| Speech to text | Voice assistants convert real-time audio into recognized text by using speech to text from the Speech service. This text is available, as it's transcribed, to both your assistant implementation and your client application. |
| Text to speech | Textual responses from your assistant are synthesized through text to speech from the Speech service. This synthesis is then made available to your client application as an audio stream. Microsoft offers the ability to build your own custom, high-quality Neural Text to speech (Neural TTS) voice that gives a voice to your brand. |
Get started with voice assistants
We offer the following quickstart article that's designed to have you running code in less than 10 minutes:
Sample code and tutorials
Sample code for creating a voice assistant is available on GitHub. The samples cover the client application for connecting to your assistant in several popular programming languages.
- Voice assistant samples on GitHub
- Tutorial: Create a Custom Commands application with simple voice commands
Customization
Voice assistants that you build by using Speech service can use a full range of customization options.