AI models to accurately convert audio files, video files, and live audio streams into text at scale.
AI models to summarize speech, detect hateful content, spoken topics, and more.
Introducing LeMUR, our new framework for applying powerful LLMs to transcribed speech
With a single line of code, LeMUR can quickly process audio transcripts for up to 10 hours worth of audio content, which effectively translates into ~150k tokens, for tasks like summarization and question answer.
We've released our new Conformer-1 model for speech recognition. Conformer-1 was trained on 650K hours of audio data and is our most accurate model to date.
How ChatGPT actually worksblog
Since its release, the public has been playing with ChatGPT and seeing what it can do, but how does ChatGPT actually work?
Learn more about how the AssemblyAI API can target and analyze data at scale across a myriad of media sources.
Media services trust AssemblyAI. Join them.
Changing our transcript provider to AssemblyAI was probably one of the smartest decisions we made. Not only the accuracy is better but they support cutting edge features that can empower your product to do more. We did a benchmark across multiple providers and they were the clear winner. The team is great, super responsive and does a great job keeping us informed about new features and updates.
Nuno S./Co-founder, Screenloop