Use the Node.js and React components to create a web application that takes sound from your microphone or file and writes the speech as text. The application uses IBM® Watson ™ Speech to Text technology to provide a range of templates and support for multiple languages. Watson Speech to Text is available in IBM Cloud and with the Watson API suite in IBM Cloud Pak® for Data.
A speech-to-text web application built with React components and a Node.js server takes audio input from your microphone or file. The audio is streamed through WebSocket to enable real-time transcription. You can view the text and update it as you speak.
The Node.js server is used for service authentication with your credentials. The web application requests a temporary ID from the server so that your credentials are not sent to your browser.
This app is designed to get you started. The Speech to Text app is a fun example, but the real results happen when you use this code to get your own app to accept speech input.
Watson Speech to Text is available in IBM Cloud and with the Watson API suite in IBM Cloud Pak for Data. With the IBM Cloud Pak for Data, you can create a Watson Speech to Text application for your own private cloud or wherever Red Hat OpenShift runs.
Once you’ve completed this code template, you’ll understand how to:
- Stream audio to Watson Speech to Text via WebSocket
- Integrate the Watson Speech to Text web application
- Use React components and the Node.js server
- The user provides audio input to the application (running locally, in IBM Cloud, or in the IBM Cloud Pak for Data application).
- The application sends audio data to Watson Speech to Text over a WebSocket connection.
- When the data is processed, the Watson Speech to Text service returns the data from the decompressed text and other metadata to the displayed application.
You will find the detailed steps of this model readme file. The steps show how to:
- Provide Watson Speech to Text.
- Enable the server.
- Use a web application.