Building with Voice LLMs | AssemblyAI

​AssemblyAI makes it easy for developers to build Speech AI into their applications using the programming languages and frameworks they already know.

​In this session, Matthew Makai, VP Developer Relations & Experience, AssemblyAI will cover how to quickly integrate high accuracy speech-to-text transcription of audio and video data into new or existing code bases. Additionally, how to use a large language model (LLM) with audio and video data using only a single line of code, and building with advanced features such as content moderation, topic detection and personally identifiable information (PII) redaction.

​This session is designed for CTOs, data science leaders, and engineering leaders who are exploring voice LLMs in their tech stacks.