Milano-based Voiseed demonstrated its web-based Revoiceit platform at CES, pitched as the best way to manage synthetic voice actors, particularly ensuring that synthetic voices present realistic emotions. The company describes it as a cloud-based solution that uses “generative AI to infuse virtual voices with human emotions and prosody, creating highly expressive, lifelike audio experiences.” While Revoiceit’s most obvious feature is its Studio (imagine Adobe Audition devoted to second-by-second management of voices), it may well be the product’s forthcoming API that provides real value to developers of entertaining technology products.

Revoiceit aims to provide any creator employing artificial voice actors with highly granular control over their performance. This control extends to a comprehensive list of voice attributes: emotional affect is the banner feature, but other elements of intonation are also controllable. For example, the studio permits a user to use IPA markup (the baroque symbols you’ll find following words in dictionaries that provide a standard pronunciation guide).

The system was created to assist localization of dialogue for applications such as games, and promises the ability to provide seamless translation of dialogue into any supported language. It’s ’human in the loop’ approach marks Voiseed as yet another company carefully considering real-world workflow in the design and presentation of its features. Interestingly, the company also appears proud of its ethical approach to voices, and claims a fully in-house approach with a ‘no cloning’ policy.

Given the system is already capable of setting second-by-second changes in emotional expression, at CES the company made clear its intention to expose its endpoints to developers via a yet-to-be-published API.

This is particularly interesting for applications that track the emotional state of system player characters in games or interactive entertainment, where their emotional state may be affected by a human audience member, or even another character. A developer could simply concentrate on the logic of the game, and the affect presented by SPCs could be controlled by Voiseed.