OpenAI's Whisper API in Node.js

--- type: transcript date: 2023-03-03 youtube_id: gddNRAxnJhE --- # Transcript: OpenAI's Whisper API in Node.js I'm going to show you how to use open ai's whisper API to transcribe audio files into text from node.js we'll walk through the steps of setting up our environment obtaining an API key and finally writing some code to transcriber audio file let's get started first let's talk about how to set up the environment in your terminal you'll want to run the following commands npm knit y this will initialize a new npm project next we're going to type npmi.env axios form data this will install the required packages that we're going to be using and finally we're going to type touch index.js and Dot EnV this will create your index file and a new DOT EnV file then you'll need to navigate to the openai website and create an account and generate an API key once you have the key you'll want to add it to the dot EMV file like so open AI underscore API underscore key equals and paste in your key there now let's take a look at the code first we're going to be importing the required packages dot EnV axios FS path and form data we're also setting up our API key to be a constant called open AI API using the process.env next we're defining a constant called file path that points to the audio file we want to transcribe next we have another constant called Model this specifies which model we want to use for the transcription after that we create a new form data object and append the model and audio file to it then we use axios to send a post request to the openai api's transcription endpoint passing the form data object as the data payload we also want to include our API key in the headers and specify the content as multi-part form data if the request is successful the API will return the transcription as a response which we log to the console and that's it with just a few lines of code you can transcribe audio using the power of the open AI API