Skip to main content

Build with AI models that can transcribe and understand audio

With a single API call, get access to AI models built on the latest AI breakthroughs to transcribe and understand audio and speech data securely at large scale.

About AssemblyAI

AssemblyAI provides AI models to transcribe and analyze audio and speech data through our production-ready, scalable web API. Our models are customizable and enable features such as content moderation, sentiment analysis, PII redaction, key phrase identification, and speaker diarization.

LeMUR, our new our new framework for applying powerful Large Language Models (LLMs) to transcribed speech, can quickly process audio transcripts for up to 10 hours worth of audio for tasks like summarization, question & answer, and AI coaching feedback.

Getting started

The AssemblyAI CLI is the fastest way to get started with the AssemblyAI API. The CLI provides an intuitive way to access the API and perform various tasks, such as uploading audio and video files for transcription and retrieving results.

Learn more


Discover how to use the AssemblyAI API with our detailed guides. You can also follow along with the examples in our Colab Notebook.

Transcribing. Transcribe audio and video files using the AssemblyAI API, including code examples and tips for improving your results.


Summarizing. Get the most out of your virtual meetings with the AssemblyAI Summarization model. Extract the most important information effortlessly.


Analyze. Optimize your call center insights with the AssemblyAI API. Discover valuable information and level up your customer service.