Get Started
🔑 Get a Free API Token https://www.assemblyai.com/
📝 API Docs https://www.assemblyai.com/docs
✍️ Projects/tutorials https://www.assemblyai.com/blog/tag/tutorials/
Contents
What is AssemblyAI?
What can you do with AssemblyAI?
What are some practical examples of using AssemblyAI?
Need help?
FAQ
👋 What is AssemblyAI?
AssemblyAI is an API that automatically transcribes audio and video files with human level accuracy. Accurately convert speech to text, in real-time or on pre-recorded audio/video files, by applying AssemblyAI's powerful deep learning models with an easy-to-use API.
Additionally, you can build powerful applications with Audio Intelligence features like Summarization, Entity Detection, Content Moderation, Sentiment Analysis, PII Redaction, and more.
🧐 What can you do with AssemblyAI?
<aside>
💡 Core Transcription
</aside>
- Asynchronous Transcription: Transcribe audio and/or video files asynchronously.
- Real-Time Transcription: Transcribe audio-streams in real-time. (Requires you to upgrade your account - reach out to an AssemblyAI team member)
- Speaker Labels: Detect number of speakers in the audio and know "Who Spoke When?"
- Word Timings: Get word-by-word timestamps across the entire transcript text.
- Profanity Filtering: Automatically detect and replace profanity in the transcription.
<aside>
💡 Audio Intelligence
</aside>
- Topic Detection: Automatically determine topics discussed in your audio or video files.
- Entity Detection: Identify a wide range of entities that are spoken in your audio files, such as person and company names, email addresses, dates, and locations.
- PII Redaction: Automatically detect and replace sensitive data (e.g., credit card numbers) in the transcription.
- Auto Chapters: Generate a "summary over time" for audio/video files. Auto Chapters works by first segmenting your audio files into logical "chapters" as the topic of conversation changes, and then provides an automatically generated summary for each "chapter" of content.