Artificial intelligence is already enabling stations to replicate the voices of on-air talent. Now a new Benztown product uses AI to craft “listener” audio for on-air use.
The audio imaging company says its AI Listener Voice Generator is designed to aid with the challenges stations may have in collecting actual listener audio. While it raises questions of transparency and other concerns, Benztown CEO Andreas Sannemann says the new tool makes “an audio producer’s job easier and more efficient than ever.”
The product offers Text-to-Speech (TTS) capabilities, including Speech-to-Speech technology that Benztown says accurately captures subtle variations in intonation. Users have access to multiple voice types and can easily adjust parameters such as speed and tone to customize the generated audio that best meets their specific needs, the company says.
“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,” Sannemann said in a release. “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.”
The tool is now available for all formats on the Benztown Library Platform for broadcast radio stations only.