A ground-breaking Expressive Text-To-Speech platform to create emotionally resonant virtual voices

Introduction

Traditional voice production processes by voice actors in a studio environment are expensive, time-consuming, and difficult to adapt to multiple languages.

Challenges with Current Solutions

Text to speech (TTS) solutions available in the market are trying to overcome the bottlenecks in the traditional voice production pipeline, but they fail to deliver the same level of emotion and prosody of human voices.

Voiseed's Innovative Approach

To overcome these problems, Voiseed designed a ground-breaking Expressive TTS platform, driven by proprietary deep learning algorithms, to create virtual human-like voices that are emotionally resonant through a cost-efficient and time-saving process.

Voice as a Service

Voiseed will offer Voice as a Service so that entertainment, e-learning, and advertising companies will be enabled to generate and dub virtual voices into any target language, while keeping the required prosody.

Project Goals

During the project, Voiseed aims to develop a high-quality unique expressive speech data set to release on the market a platform with:

1. More than 32 emotions
2. Support for 16 languages