Effortless Audio Transcription with DeepGram API (Full Transcript)

Speaker 1: Here's how you can transcribe any audio that you want. First, we'll have to use an AI. Today, we're gonna use DeepGram. Now let's grab our imports. Obviously, we have to import DeepGram. Also, we'll use ASICIO, JSON, and OS in order to make things a little bit easier. Now comes the fun part. To instantiate our AI, we'll use an API key. Then, we'll set up our parameters. Our parameters are just a dictionary. Here, I'm saying we're using a general AI transcription model. And here, I'm making sure we're using the enhanced version. Now let's actually transcribe. Here's our directory of audios. And for every audio in this directory, I'm gonna open it up as an MP3 and literally just call a single function. You can find this function in the DeepGram documentation. Finally, we're gonna dump our transcript as a JSON into a file path that we specified. I'm using ASICIO to make sure we're parallelizing as much as possible. That way, we're running as fast as possible. But overall, to transcribe, that's all you need to do. Set up the AI model, open up your audios, and call the transcription function. And at the end, you should have JSONs that look like this. All that's left to do is parse. Follow DeepGram for more AI content.