AssemblyAI Documentation

Build with our leading Speech AI models

Universal-2 is live

Dive into our research paper to see how we're redefining speech AI accuracy. Read more here.

Quickstart

Get started with our SDK guides in minutes:

Transcribe an audio file

Transcribe streaming audio from microphone

Ask questions and summarize audio content with LLMs

AssemblyAI SDKs:

Learn about the API

API reference

FAQ

Supported languages

Concurrency limit

Additional resources

Examples

Integrations

Playground

AssemblyAI CLI

Products

Speech-to-Text

Models for converting audio files, video files, and live speech into text.

LeMUR

LeMUR is a framework for applying Large Language Models (LLMs) to spoken data.

Audio Intelligence

Models for interpreting audio for business and personal workflows.

Need help? Talk to our Support team

Join our Discord community

Check status page

See changelog