This open-source repo provided by AssemblyAI displays how to use our real-time API in the browser!
In this app, we grab an audio stream from the user's computer and then send that over a WebSocket to AssemblyAI for real-time transcription. Once AssemblyAI begins transcribing, we display the text in the browser. This is accomplished using Express for our backend and Vanilla JavaScript with the npm package recordrtc for our frontend.
- Before running this app, you need to upgrade your AssemblyAI account. The real-time API is only available to upgraded accounts at this time.
- Running the app before upgrading will cause an error with a 402 status code.
⚠️ - To upgrade your account you need to add a card. You can do that in your dashboard here!
- Clone the repo to your local machine.
- Open a terminal in the main directory housing the project. In this case
realtime-transcription-browser-js-example
. - Run
npm install
to ensure all dependencies are installed. - Add your AssemblyAI key to line 13 of
server.js
- Start the server with the command
npm run server
(will run on port 8000). - Open a second terminal in the main directory of the project and start the client side with
npm run client
(will run on port 3000).