Welcome to Speechly Docs

With Speechly you can easily add voice functionalities to any user interface. We provide speech-to-text and natural language understanding features, both accessible via a simple API using ready-made client libraries. All you need to do is provide a small amount of training data for our machine learning models, and integrate one of the client libraries to your application.

The documentation is divided into the following sections (also shown in the menu to the left):

  • Quick Start goes through the basic steps to set up your first voice application in the Speechly Dashboard. Also check out our five-part video tutorial about How Speechly Works.
  • Development Tools gives an overview of our library offering, as well as provides instructions on how to use our Dashboard and Command Line Tool.
  • Client Libraries shows how to start integrating Speechly to your application using our Client libraries (available for Web, React, iOS and Android).
  • Configuration teaches you how to provide training data for the machine learning models that underlie everything that happens behind the scenes.
  • Design provides some high-level guidelines on how to design a responsive multi-modal voice user interface.
  • Speechly gRPC API contains a description and reference of our low-level gRPC API. (For advanced users only!)
  • FAQ is for the Frequently Asked Questions
  • Product updates lists recent updates to our products.

I Need Help

Please post a question at our Github discussions page or for a more concrete technical problem, please file an issue.

Try to be as specific as you can. Describe what you are trying to do, how you do it, and what errors (if any) you are getting. We are happy to help you forward!

Profile image for Antti Ukkonen

Last updated by Antti Ukkonen on January 19, 2022 at 14:20 +0200

Found an error on our documentation? Please file an issue or make a pull request