AI startup Sonantic says its tech captures new subtleties of speech
in recent years, but there are still aspects of human speech that escape synthetic imitation. Sure, AI actors can deliver smooth corporate voiceovers for presentations and adverts, but more complex performances — a convincing rendition ofSonantic, an AI voice startup, says it’s made a minor breakthrough in its development of audio deepfakes, creating a synthetic voice that can express subtleties like teasing and flirtation.
In the video below, you can hear the company’s attempt at a flirtatious AI — though whether or not you think it captures the nuances of human speech is a subjective question. On a first listen, I thought the voice was near-indistinguishable from that of a real person, but colleagues atsay they instantly clocked it as a robot, pointing to the uncanny spaces left between certain words, and a slight synthetic crinkle in the pronunciation.
Sonantic CEO Zeena Qureshi describes the company’s software as “Photoshop for voice.” Its interface lets users type out the speech they want to synthesize, specify the mood of the delivery, and then select from a cast of AI voices, most of which are copied from real human actors. This is by no means a unique offering but Sonantic says its level of customization is more in-depth than that of rivals’.
Emotional choices for delivery include anger, fear, sadness, happiness, and joy, and, with this week’s update, flirtatious, coy, teasing, and boasting. A “director mode” allows for even more tweaking: the pitch of a voice can be adjusted, the intensity of delivery dialed up or down, and those little non-speech vocalizations like laughs and breaths inserted.“I think that’s the main difference — our ability to direct and control and edit and sculpt a performance,” says Flynn.
To try and get a raw and representative sample of Sonantic’s technology, I asked them to render the same line using a handful of different moods. You can listen to them yourself to compare.
Ireland Latest News, Ireland Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Listen to The Ben Joravsky Show - Chicago ReaderSenior writer Ben Joravsky riffs on the day's stories with his celebrated humor, insight, and honesty, and interviews politicians, activists, journalists and other political know-it-alls. The show is available by 4 p.m. Tuesdays through Fridays at chicagoreader.com/joravsky or on the Reader's YouTube channel—or wherever you podcast. Don't miss Oh, What a Week!--the Friday feature in which Ben & producer Dennis (aka, Dr. D.) review the week's top stories. Also, bonus interviews drop on Saturdays, Sundays and Mondays.
Read more »
AI and humans: Will the technology end up replacing us?How do humans measure up to supercomputers? In what ways – if any – are we irreplaceable? Find out more information at engineering
Read more »
Engineering student's AI model turns American Sign Language into English in real-timeEngineering student Priyanjali Gupta's pre-trained AI model translates some American Sign Language signs to English instantly.
Read more »
SJSU opens one-of-a-kind, fully-autonomous AI-powered store on campus'When you go back and read Dystopian and other types of books about the future, you always talk about just being able to walk into stores and walk right out and have food you want,' SJSU Senior Nicholas Mackie said. 'Now it's here and now we can do it.'
Read more »
Cow, Bull, and the Meaning of AI EssaysEssays can be marvelous and sublime; they can also be churned from content mills. Where does the AI-written variety fit?
Read more »