Skip to main content

Elsa speech assessment API


The Elsa API enables developers to create AI-powered applications that can evaluate the accuracy of spoken English communication through speech. With advanced machine learning technology, the ELSA API offers an easy-to-use development interface for integration into applications.

This API can analyze both scripted (with a transcript) and unscripted English speech recordings, making it ideal for assessing communication skills in spontaneous speech. The ELSA AI technology evaluates spoken English based on five major dimensions of communication: pronunciation, prosody, and fluency in both scripted and unscripted recordings, as well as grammar and vocabulary in unscripted recordings. It provides feedback in all cases to help users understand their mistakes and improve their spoken communication skills.

Before you get started

Before starting to use the API you need to receive an API key from ELSA. This is used to authenticate every single call with ELSA servers. If you do not yet have a key, fill out this request form or email and an ELSA representative with get in touch with you.