Artificial intelligence company WellSaid Labs has unveiled
groundbreaking technology that enables users to control the emotional delivery and vocal characteristics of AI-generated speech, similar to how directors work with voice actors in recording sessions.
The Kirkland, Washington-based enterprise announced their latest AI model, called Caruso, which introduces innovative “emotional directing” capabilities. This advancement allows users to manipulate various aspects of synthetic voice recordings, including emotional tone, pitch modulation, and speaking tempo.
Beyond emotional control, the new model brings enhanced efficiency through faster audio generation and improved pronunciation accuracy. According to WellSaid’s Chief Executive Officer Brian Cook, this technology aims to minimize the need for multiple recording attempts by producing accurate voice clips on the initial try.
Cook, who detailed the announcement in a public statement, emphasized how the model will streamline the audio production process by reducing time spent on regenerating voice clips. The CEO, who previously led Nintex and founded Incredible Capital, joined WellSaid Labs’ leadership team in early 2024, marking a year in his current role.
The company has positioned itself as a responsible player in the enterprise AI voice sector, implementing specific protocols and ethical guidelines designed to ensure appropriate use of their technology. This approach helps distinguish WellSaid Labs within the competitive landscape of AI voice generation.
WellSaid Labs’ journey began at the Allen Institute for Artificial Intelligence (AI2) Incubator in Seattle, where it was initially developed before spinning off as an independent company. The firm’s growth has been supported by significant investment, including a Series A funding round that secured $10 million in 2021, with Fuse taking the lead investor position.
The company’s current leadership structure includes Matt Hocking, who serves as both co-founder and executive chairman, working alongside Cook to guide the organization’s strategic direction. Their focus remains on developing AI voice solutions that cater to enterprise clients while maintaining high ethical standards in artificial intelligence implementation.
This latest development in AI voice technology represents a
significant step forward in making synthetic speech more nuanced and emotionally responsive. The Caruso model’s ability to incorporate directorial input into AI voice generation could potentially transform how businesses approach audio content creation, from corporate communications to entertainment applications.
The technology builds upon WellSaid Labs’ existing foundation in the AI voice space, where they have established themselves as a company committed to responsible innovation. Their approach combines technical advancement with ethical considerations, addressing growing industry concerns about the responsible development and deployment of AI technologies.
As enterprises increasingly adopt AI-powered solutions, WellSaid Labs’ new model arrives at a time when demand for sophisticated,
controllable voice technology is growing. The company’s focus on getting voice generation right on the first attempt addresses a common pain point in audio production workflows, potentially saving significant time and resources for organizations that regularly produce voice content.
The introduction of emotional directing capabilities in AI voice generation represents another milestone in the evolution of synthetic speech technology, pushing the boundaries of what’s possible while maintaining a focus on practical business applications and ethical deployment.