These features make it easy to build great audio experiences for your application.



Asynchronous TTS engine

Create text to speech and retrieve it after a short delay.

Synchronous TTS engine (via web socket)

Create text-to-speech and retrieve it almost in real-time.


Create audio from simple text inputs only.

Voice selection

Select from over 250+ (and growing) voices you can integrate with us and don’t need to integrate with multiple providers.

Script creation & versioning

Import or create your own script and version it (e.g. for personalization or to make it dynamic).

Voice cloning

Voice Cloning allows you the ability to with about 30 minutes of data to clone your voice. We have an application for cloning your voice - so reach out to us to gain access. Note that only you will be able to access your voice for your applications if your voice is specific to your brand.

Rendering engine

API.audio's proprietary rendering engine allows you to seamlessly scale your audio production; no matter how big your project will get.

Entity verification (coming soon!)

API.audio proprietary entity verification system helps to verify the pronunciation of names, and also let's you know what countries are supported. So far we support upwards of 5k first names and 200 plus major cities and 100 plus country names and are adding more with time.


Didn't find the feature you're looking for?

Contact [email protected]


Enterprise features

Some of the features below such as Sync TTS and Voice Cloning can be accessed through our enterprise plan. Contact [email protected] to find out about more.

Client Libraries:

More coming soon!

Did this page help you?