Sonantic releases the next breakthrough: AI voices that can shout
Comunicato Precedente
Comunicato Successivo
Sonantic's product is evolving alongside its technology, and our team of experts work to continuously expand our text-to-speech(TTS) capabilities. To demonstrate our new shouting feature, we created a relatable scene that illustrates how shouting allows for increased intensity and more compelling narratives. In the demo, we hear a couple having an everyday conversation which quickly escalates, with shouting bringing it to its emotional climax.
Believable TTS shouting requires more than simply turning up the volume, as Co-Founder and CTO John Flynn explains, "To accurately model shouting we had to do some hard research to focus the models on the exertion and strain of the voice. This then gives that realistic sound - it's true shouting."
As projection is its own vocal control, the new shouting feature offers an additional method for shifting tone and conveying a stronger or more urgent message. In the scene, shouting is used to illustrate intense anger and emotional pain felt by the two lovers, but there are many other use cases for shouting. Shouting helps convey a range of needs in storytelling from indicating distance, urgency, joy, encouragement, or even the noise levels of a character's location. Text-to-Speech shouting offers our clients the opportunity to create entirely new, compelling narratives, while preserving actors' vocal cords and allowing them to earn passive income.
Ready to hear AIs get emotional?
Click here.
Read the full blog post here.
Sonantic Press Contact:
Zeena Qureshi (CEO & Co-founder) and
Carles Reina (VP Customers & Strategy)[email protected]
Ufficio Stampa
PR Newswire (Leggi tutti i comunicati)
209 - 215 Blackfriars Road
LONDON United Kingdom




