Hume launches new text-to-speech model Octave that generates custom AI voices with adjustable emotions.
Author: DNyuz | Source: DNyuz | Read the full article
Hume AI, a startup based in New York City, has recently unveiled a groundbreaking text-to-speech model named Octave. This innovative technology is designed to create realistic and emotionally expressive AI voices for various applications, such as audiobooks, video games, and films. Unlike traditional text-to-speech systems, Octave utilizes a large language model that understands context and can adjust the tone and emotion of the speech based on the content it reads.
One of the standout features of Octave is its ability to interpret character traits and emotions from scripts, allowing it to deliver lines with the appropriate inflection. For instance, it can convey sarcasm or urgency without needing specific instructions. Users can also customize the generated voices by simply typing in their desired emotional adjustments, making it a versatile tool for content creators looking for unique character voices.
Hume AI's Octave is not only focused on English but also supports Spanish, with plans to expand to more languages in the future. The model is designed for offline use, meaning it generates audio files that can be integrated into various projects. With competitive pricing and a user-friendly API, Octave aims to provide creators with high-quality, customizable voice options that enhance their storytelling capabilities.
