API.audio provides the world’s first Audio-as-a-Service platform - allowing you to ship audio in seconds to your customers!

Api.Audio makes producing audio assets 100x faster, 99% cheaper, and is super simple even for devs like you.

Developers use Aflorithmic’s API.audio to easily integrate Text-to-Audio into their product offerings and processes in order to either automate audio production or allow end users without audio expertise to create high quality audio.

It provides all the backend services you need to build an audio product. You can use it completely, or just the services you require:

Content Management
Individual content pieces (scripts) can be organised into modules and projects which are the base to efficiently mass version and produce audio.
Roles and Permissions
User management with enterprise-grade security built in
Speech Functions
Human quality AI-speech functions that are distributed globally
Production (Mastering)
Our proprietary audio enhancement (mixing and mastering) engine allows you to produce beautiful audio in any format
Produce thousand of audio assets in seconds
Discover the perfect sound for your audio asset

To get started you need:

  1. An API key (its free!)
  2. An understanding of python, bash or javascript.
  3. Create your first audio asset by using our audio production capabilities and share with your friends!

First audio asset

Let's produce an audio asset (like an mp3) in a few seconds. You'll need an API KEY (it's free) and to pip install apiaudio.
Everything else should run out of the box.

import apiaudio 
import os
apiaudio.api_key = os.environ['APIKEY']
audio_creation = apiaudio.Orchestrator.create_audio(scriptText="Hi nerds, wouldn't it be cool to\
build an audio message in 5 lines of code", voice="Liam", soundTemplate="workinprogress")

# You'll see a file downloaded

Now you can listen to your audio asset. Have some fun!


  • Turn any text into speech in seconds
  • Versioning and personalisation of content programmatically
  • Create beautiful audio (speech plus sound designs) in seconds.
  • Scale up horizontally without having to set up any infrastructure
  • 600+ voices
  • 50+ sound effects and 100+ sound designs
  • 60 plus languages
  • Caching, webhooks and low latency text to speech


We recommend you start with a Hello World (takes <10min to complete).


Questions? Need help with integration?

Contact us at [email protected] or [email protected]

Sign Up For Product Updates

* indicates required

What’s Next

View Developer Tutorials