Live webinar on 09/28: Improving Human-to-Machine Conversations with OneReach.ai! ūüó£ Register Here

nodejs, python, sdk

Build With the Official Deepgram SDKs

BY Michael Jolley  | July 22 2021

We love empowering our developer communities to take full advantage of voice in their applications. So, we’re announcing two new official SDKs for Node.js and Python. Both of these SDKs make it easier than ever to add automated speech-to-text recognition to your applications.

How Easy Is It?

To get started, make sure you have a Deepgram account by signing up at https://console.deepgram.com/signup. After signing up, log in and get an API key. Then, in your terminal, run the appropriate command below to install the SDK.

Node.js

npm install @deepgram/sdk

Python

pip install deepgram-sdk

Once the SDK has been installed, the following snippets will allow you to transcribe a prerecorded audio file. Be sure to replace YOUR_DEEPGRAM_API_KEY with the API key, you created earlier.

Node.js

const { Deepgram } = require('@deepgram/sdk');

const deepgramApiKey = 'YOUR_DEEPGRAM_API_KEY';

function main() {
  return new Promise((resolve, reject) => {
    (async () => {
      try {
        const deepgram = new Deepgram(deepgramApiKey);

        const transcription = await newDeepgram.transcription.preRecorded({
          url: 'https://static.deepgram.com/examples/Bueller-Life-moves-pretty-fast.wav'
        }, {
          punctuate: true
        });
        console.dir(transcription, { depth: null });
        resolve();
      }
      catch (err) {
        console.log(`Err: ${err}`);
        reject(err);
      }
    })()
  });
}

main();

Python

from deepgram import Deepgram

import asyncio, json

DEEPGRAM_API_KEY = 'YOUR_API_KEY'

async def main():

    # Initializes the Deepgram SDK

    dg_client = Deepgram(DEEPGRAM_API_KEY)

    source = {'url': 'https://static.deepgram.com/examples/Bueller-Life-moves-pretty-fast.wav'}

    response = await dg_client.transcription.prerecorded(source)

    print(json.dumps(response, indent=4))

asyncio.run(main())

Contributions Welcome

Our SDKs are still in their infancy, but we’re building them in public. We welcome all issues and pull requests to our Node.js and Python repositories. Of course, we’d also love to hear what you’re building, so tweet at @DeepgramDevs and let us know!

Finally, a reason to get excited about voice recognition.

Check out Deepgram

Apply Now

Receive up to $100,000 to use over 12 months.

Become a Partner

When you become a partner you’re in good company.

Talk to Customer Success