Last year, OpenAI released Whisper, an open-source speech recognition model that allows users to transcribe audio into text. Since then there has been an increased appetite to integrate speech recognition into products from developers and corporate teams alike. As a result, OpenAI recently made the Whisper model available via an API. If your application relies on speech recognition or natural language understanding (NLU), you’ve probably questioned whether it’s worth spinning up internal resources to deploy open-source software, or whether it’s easier to use an off-the-shelf speech recognition solution.

This webinar aims to answer those questions and showcase how to build a voice application with Whisper.