In an exclusive interview at the National Association of Broadcasters' recent event, NAB Show 2024, Grant Reaber, co-founder and Chief Research Officer of Respeecher, provided insights into the company's groundbreaking advancements in AI voice cloning technology and its transformative impact on the film and television industry.
Founded in 2018, Respeecher has been at the forefront of harnessing the potential of generative AI, particularly in text-to-speech synthesis and speech-to-speech synthesis. Reaber, reflecting on the genesis of Respeecher, cited the key breakthroughs in AI, such as GANs and WaveNet, which inspired him to explore the possibilities of realistic audio generation.
One of Respeecher's most compelling applications is localization, which allows content creators to adapt their productions for multiple markets effortlessly. By integrating with various localization platforms, Respeecher streamlines workflows and enables using the original actor's voice in different languages, opening up new avenues for global content distribution.
Grant Reaber elaborated on the versatility of Respeecher's solutions, ranging from text-to-speech for localization to speech-to-speech conversion for diverse applications. Notably, Respeecher's technology can preserve emotional nuances in speech, offering unprecedented control over voice modulation and expression.
However, Reaber acknowledged the evolving challenges in achieving controllability and addressing AI ethics. Respeecher is committed to ensuring fair compensation, consent, and control for voice actors through innovative approaches, including integrating actors' voices into the platform and facilitating broader opportunities for creative expression.