AssemblyAI Documentation
Explore our guides and code examples to learn how to get started with transcribing and understanding audio data.
Try it out
The AssemblyAI CLI is the fastest way to get started with the AssemblyAI API.
Browse models
Explore our AI models for transcribing and analyzing audio and video data.
Core Transcription
Models for converting audio files, video files, and live speech into text.
Audio Intelligence
Models for interpreting audio for business and personal workflows.
Summarization
Automatically summarize audio and video data with custom summary types.
Content Moderation
Detect sensitive content, such as hate speech, violent language, and sensitive social issues.
Auto Chapters
Generate chapter summaries over time for audio and video files.
Key Phrases
Accurately identify significant words and phrases to extract highlights from you audio or video data.
Sentiment Analysis
Detect sentiment for each sentence with detailed analysis of the positive, negative, or neutral sentiment conveyed in the audio.
Entity Detection
Identify person and company names, email addresses, dates, and locations.
PII Redaction
Identify and remove Personally Identifiable Information (PII), such as names, phone numbers, and social security numbers.
Topic Detection
Detect and label topics using standardized IAB taxonomy.
LeMUR
LeMUR is a framework for applying Large Language Models (LLMs) to spoken data.
- Generate custom summaries of transcripts.
- Ask questions about what was said.
- Get feedback through concrete action items.
- Define your own custom prompts.