Benztown’s Imaging Libraries are adding an artificial intelligence touch – the company has announced the launch of an AI Listener Voice Generator. Instead of creating AI air talent, the technology here is designed to synthesize “listener” audio for on-air purposes.
The AI Listener Voice Generator uses both Text-to-Speech and Speech-to-Speech capabilities, enabling users to create natural-sounding audio with nuances in intonation. With a range of voice types and adjustable parameters like speed and tone, the tool allows for the customization of audio to fit specific production requirements.
This is Benztown’s latest effort to combat the growing difficulty of gathering listener audio from the public, in addition to its Role Callers service introduced last August. Currently, the AI Listener Voice Generator is accessible to subscribers of the Benztown Library Platform catering to broadcast radio stations.
Benztown CEO Andreas Sannemann said, “We are excited to provide our library users with the most compelling listener material possible; the listener audio they actually need for every specific piece of production. Benztown’s AI Listener Voice Generator is another giant step forward in creating great-sounding radio with next-generation technology through AI-generated listeners on demand.”
