deepgram
From the YC post:
DeepGram is a company launching out of our Winter 2016 class that uses deep learning to index audio and make it searchable for businesses. For example, a company can use DeepGram to analyze their phone support audio dataset and search for moments where their competitors' names are mentioned.
This project provides a simple NodeJS wrapper for the Deepgram API, it's built on top of frisbee.
This is a very early version, I hope to implement more functions & enhance the existing ones in the following weeks, PRs are welcome 😄.
Usage
There's a NPM package available:
npm install --save deepgram
Indexing an audio file is as easy as:
deepgram.indexContent( 'http://website.com/audio.mp3' ).then( data => {
// you'll get the content ID here (inside data)
})
Examples available here.
Development
The wrapper uses Babel. You may test the source using mocha:
npm test
The above will compile the JS & run mocha with the options in the file.
API Documentation
I found the API documentation here.
When you signup on the website you'll see some curl samples as well.
TODO
- It could be interesting to use this module directly from the browser.