Overview

Discover what you can build with the AssemblyAI API with real-world code examples.

For examples using the API without SDKs, see API guides.

Popular​

How to Transcribe YouTube VideosSpeech-to-Text

How to Generate Subtitles for VideosSpeech-to-Text

Identify Speakers in Audio RecordingsAudio Intelligence

Use LeMUR with Streaming Speech-to-TextStreamingLeMUR

Create Summarized Chapters from PodcastsSpeech-to-Text

Use LeMUR to Boost Custom Vocabulary ListLeMUR

All​

Creating summarized chapters from podcasts	Audio Intelligence
Identifying hate speech in audio or video files	Audio Intelligence
PII redaction using entity detection	Audio Intelligence
Identifying highlights in audio and video files	Audio Intelligence
Identifying speakers in audio recordings	Speech-to-Text
Summarizing virtual meetings	Audio Intelligence
Transcribing multiple files simultaneously	Speech-to-Text
Splitting audio files into shorter files	Speech-to-Text
Route to a default language if ALD confidence is low	Speech-to-Text
Guide to Common Errors for New AssemblyAI Users	Speech-to-Text
Deleting an AssemblyAI transcript	Speech-to-Text
Detecting low confidence words in a transcript	Speech-to-Text
Do more with the JavaScript SDK	Speech-to-Text
Build a UI for transcription with Gradio and Python	Speech-to-Text
Iterate over Speaker Labels with Make.com	Speech-to-Text
How to implement retry server error logic	Speech-to-Text
How to implement retry upload error logic	Speech-to-Text
Schedule a DELETE request with AssemblyAI and EasyCron	Speech-to-Text
Creating subtitles with speaker labels	Speech-to-Text
Create a speaker timeline	Speech-to-Text
Specifying a language	Speech-to-Text
Create custom length subtitles with AssemblyAI	Speech-to-Text
Generating subtitles for videos	Speech-to-Text
Speaker identification across files w/ AssemblyAI, Pinecone, and Nvidia’s TitaNet model	Speech-to-Text
Transcribing an audio file	Speech-to-Text
Transcribing from an S3 bucket	Speech-to-Text
How to get YouTube video transcripts with yt-dlp	Speech-to-Text
Transcribing files hosted on GitHub with AssemblyAI	Speech-to-Text
Guide to using Google Drive links with AssemblyAI	Speech-to-Text
Translating an AssemblyAI subtitle transcript	Speech-to-Text
Translating an AssemblyAI transcript	Speech-to-Text
Leverage LeMUR for customer call sentiment analysis	LeMUR
Estimating input token costs with LeMUR	LeMUR
Boosting transcription accuracy with LeMUR (LeMUR custom vocab)	LeMUR
Extract dialogue data with LeMUR and JSON	LeMUR
Creating chapter summaries with LeMUR’s custom text input parameter	LeMUR
Processing speaker labels with LeMUR’s custom text input parameter	LeMUR
Automatically generate action items from a meeting with LeMUR	LeMUR
How to pass context from previous LeMUR requests	LeMUR
Implement a sales playbook using LeMUR	LeMUR
Identify speakers by name with LeMUR	LeMUR
How to use LeMUR’s specialized endpoints	LeMUR
Identify action items using LeMUR’s Task endpoint	LeMUR
Receive AI coaching feedback with LeMUR’s Task endpoint	LeMUR
Summarize transcripts with LeMUR’s Task endpoint	LeMUR
Perform structured Q&A with LeMUR’s Task endpoint	LeMUR
Extracting transcript quotes with LeMUR’s custom text input parameter	LeMUR
Extracting quotes with timestamps using LeMUR + semantic search	LeMUR
Processing audio files with LLMs using LeMUR	LeMUR
Transcribe a local file in real-time in Node.js	StreamingSpeech-to-Text
Capturing complete sentences as partial transcripts with AssemblyAI	StreamingSpeech-to-Text
Using Streaming speech-to-text	StreamingSpeech-to-Text
Using LeMUR with Streaming speech-to-text	StreamingSpeech-to-Text
Terminate Streaming session after inactivity	StreamingSpeech-to-Text

API guides​

Transcribing an audio file	Speech-to-Text
Generating subtitles for videos	Speech-to-Text
Using real-time streaming	Streaming
Summarizing virtual meetings	Audio Intelligence
Identifying hate speech in audio or video files	Audio Intelligence
Identifying highlights in audio and video files	Audio Intelligence
Identifying speakers in audio recordings	Audio Intelligence
Creating summarized chapters from podcasts	Audio Intelligence
Generate meeting action items with LeMUR	LeMUR
Separating automatic language detection from transcription	Speech-to-Text
Process speaker labels with LeMUR	LeMUR