WellSaid Announces the Caruso AI Voice Model

WellSaid, an artificial intelligence voice platform provider, has launched its Caruso voice AI model, available in WellSaid Studio and equipped with new features like AI Director to enable users to adjust emotional intonation and performance.

With Caruso, WellSaid users can expect the following updates:

• Studio-quality voice narration and audio output with reduced latency.
• WellSaid's AI Director, which lets users adjust pitch, pace, and emotional intonation and instruct each script.
• Improved pronunciation with Caruso's intelligent engine, combined with Oxford phonetic spelling data, to reduce the need to modify or store mispronounced words.
• Increased team collaboration features that allow companies to integrate WellSaid into existing workflows.
• Responsible AI practices that support transparency, consent, and privacy.

"We're excited to introduce Caruso, with new architecture built from the ground up that's designed to deliver faster speeds, the highest-quality audio in the market, and a more intuitive product to give our business users a competitive edge," said Brian Cook, CEO of WellSaid, in a statement. "With these upgrades, users can enjoy AI voices that say it right the first time, drastically reducing the time and effort that goes into re-rendering audio clips, setting us apart from competing platforms. Not only will Caruso help organizations streamline workflows, but it will help them improve their bottom line."