Get Started

Create Professional Audio with AI 10,000x Faster

AudioStack enables you to create professional audio in the cloud from your code, or via our easy-to-use Platform. AudioStack API makes it easy to programmatically create human-sounding speech and audio using code, and then integrate it where ever audio is needed!


The purposes of our API documentation is to help you get up and running with AudioStack API and SDKs quickly, as well as to cover the foundational concepts shaping our platform. We recognise that many of the developers using AudioStack don't have a background in audio production, so all the main concepts are covered in these guides.


New to APIs?

We recommend you start with our Beginners' Guide, which will help you set up your development environment before creating your first audio asset.


Want to create audio without writing any code?

We offer a number of workflows to our enterprise customers, which empower everyone from sales representatives to CEOs to create professional quality audio assets using AudioStack API. Learn how to create an account.

How the AudioStack API works

Explore our API documentation and create your first audio asset right away.

API reference

The API reference guide describes all the endpoints in the API and allows you to try out making API calls directly from your browser, no installation needed.


We have a Python SDK available, and one in Javascript.

API status

Check it here:

Want to see examples of what you can build in AudioStack? Check out our example API recipes.

Technical getting started

What’s Next

Ready to get set up with AudioStack API?