“AI-coustics: Using Generative AI to Combat Noisy Audio – Can You Hear Me Now?”

by

in

– AI-coustics is a German startup using generative AI to enhance voice clarity in videos
– The technology goes beyond noise suppression and can work across various devices and speakers
– The company is funded with €1.9 million and aims to eliminate bias by recruiting diverse speech sample contributors

AI-coustics, a German startup, has emerged from stealth with €1.9 million in funding to address the challenge of poor audio quality in digital communications. The technology uses generative AI to enhance the clarity of voices in videos, offering a unique approach to noise reduction that works across various devices and speakers. Co-founded by Fabian Seipel and Corvin Jaedicke, the startup aims to make digital interactions as clear as a broadcast from a professional studio.

AI-coustics uses a model trained on speech samples recorded in their Berlin studio to simulate audio artifacts and problems during the training process. The platform has a unique approach to developing AI mechanisms for noise reduction work, focusing on recruiting diverse speech sample contributors to eliminate bias in the technology. The startup offers a web app, API, and an SDK for post-processing audio and video recordings, aiming to embed the technology in devices like soundbars, smartphones, and headphones for automatic voice clarity boost.

Despite concerns about job displacement due to mastering tech like AI-coustics, Seipel believes the technology can expedite time-consuming tasks related to audio production while maintaining high speech quality. The startup, which generates revenue through subscriptions, on-demand pricing, and licensing, has five enterprise customers and 20,000 users, with plans to expand the team and improve the speech-enhancing model. The startup received funding from Connect Ventures, Inovia Capital, FOV Ventures, and Ableton CFO Jan Bohl, positioning them for growth and innovation in the market.

Source link