Hey 👋, this weekly update contains the latest info on our new product features, tutorials, and our community.
Ask Questions About Your Audio With LLMs
LLMs make it possible to answer questions about your text data, and AssemblyAI's LeMUR makes it easy to apply LLMs to audio and video data. Our LeMUR guides will show you how to:
- Summarize your audio data with key takeaways.
- Get answers to questions about your audio.
- Generate tags, titles, and descriptions from your audio data.
Try LeMUR and get answers to any questions about your audio with LLMs. With LeMUR, you can send any prompt to the LLM and easily apply the model to your transcribed audio files.
import assemblyai as aai
aai.settings.api_key = "YOUR_API_KEY"
# Step 1: Transcribe an audio file.
audio_url = "https://storage.googleapis.com/aai-web-samples/gettysburg.wav"
transcriber = aai.Transcriber()
transcript = transcriber.transcribe(audio_url)
# Or use an existing transcript:
# transcript = aai.Transcript.get_by_id("YOUR_TRANSCRIPT_ID")
# Step 2: Apply LeMUR.
prompt = "Provide a brief summary of the transcript."
result = transcript.lemur.task(prompt)
print(result.response)
If you run the code above, you'll see the following output:
This transcript contains the opening lines of Abraham Lincoln's Gettysburg Address.
It references how the United States was founded 87 years earlier on the principles
of liberty and equality. Lincoln is remarking that the nation was created with the
idea that all people have equal rights.
For examples on how to use LeMUR in Java, TypeScript and JavaScript, check out our docs.
Fresh From Our Blog
How to do Speech-To-Text with Go: Learn how Speech Recognition can be integrated into your Go application in only a few lines of code. Read more>>
How to Get YouTube Video Transcripts: Learn how to get the transcript of a YouTube video with this easy-to-follow Python tutorial. Read more>>
Extract phone call insights with LLMs in Python: Learn how to automatically extract insights from customer calls with Large Language Models (LLMs) and Python. Read more>>
Our Trending YouTube Tutorials
How to Index Podcasts with Keywords like on Huberman's Website: Learn to build an application that indexes podcast episodes based on keywords using Speech-to-Text.
Live Speech-to-Text With Google Docs Using LLMs (Python Tutorial): Discover how to implement real-time speech-to-text transcription in Google Docs using AssemblyAI's Speech-to-text API and large language models (LLMs).
The Physics of Generative AI - How AI models use physics to generate novel data: Modern Generative AI is capable of generating entire stories and photorealistic images, but how do these models actually work?
