Resemble AI aims to bring more human-sounding AI voices to developers and creators with the launch of its speech-to-speech feature. With this new function, developers will finally be able to capture the unique style of human voices at scale through adapted machine learning.
Resemble AI is expanding creative possibilities for human voices and beloved characters through its generative audio.
With the AI’s ability to input voice replications, they can speak in different emotions, styles, and even sing without speech. The target voice also has this ability.
“We are using the AI at Resemble to develop more professionally produced voices to use for our hit podcast ‘Animals Anonymous,’” says co-founder of Fika Agency Adam Altman. “Now our entire team can record new episodes that feel consistent with the same voices our listeners are used to hearing.”
A team of researchers at Resemble AI used 3 minutes and 12 seconds of voice recordings by Andy Warhol to create synthetic voice narration for the Emmy award-winning and Dorian Award-winning documentary series, The Andy Warhol Diaries. They adjusted the emotion and pitch to make them more human-like in the AI output by including audio reference clips from another speaker. This is how Style Transfer works in action.
“Resemble AIʼs mission is to make interactions with digital products as human and natural as possible,” says Resemble AI founder and CEO Zohaib Ahmed. “We have dramatically accelerated and simplified the process of creating human-like AI voices by building hyper-realistic synthetic voices that can match or expand the reach of voice actors. This means that developers, creators and storytellers can create content in any language, and with any voice, without the need for expense or travel associated with recording studios.”
Customers on the Basic, Pro, and Enterprise plans can now use speech-to-speech in order to provide detailed information within their projects. Instead of using text as input, audio files that are uploaded or recordings that are recorded for this feature are accepted. This allows for more quality AI voices and allows for a voice talent to speak a language different than their original voice.