Faster Audio File Handling and Improved Error Messages
Discover weekly product updates, latest blogs and YouTube tutorials.



Hey 👋, this weekly update contains the latest info on new product features, tutorials, and our community.
⚡️Product Updates
Check out the AssemblyAI changelog for the latest product improvements made by our team:
- Faster transcription speed: Enhanced file handling has reduced latency by a minimum of 3 seconds across all audio files, with significant improvements for larger files from external URLs.
- More clarity for error messages: Refined for better understanding, especially during internal server errors.
- Rivet integration: Updated to be compatible with AssemblyAI's latest Node SDK.
- API status: Stay informed with real-time updates on our status page.
LeMUR: Build LLM apps on voice data
LeMUR is the easiest way to code applications that apply LLMs to speech. In just a few lines of code you can search, summarize, ask questions, and generate new text, on all of your audio and video.
Check out the following popular cookbooks for using LeMUR:
- Customer Call Sentiment Analysis with LeMUR.
- Dialogue Data Extraction using LeMUR and JSON.
- Automatically Generate Action Items from a Meeting with LeMUR.
- Sales Playbook Implementation with LeMUR.
- Audio File Processing with LLMs through LeMUR.
- Transcript Citation Extraction using OpenAI Embeddings.
Fresh From Our Blog
Combining Speech Recognition and Diarization in one model: A new approach towards multi-speaker speech processing integrates Speaker Diarization and Automatic Speech Recognition in a unified framework. We discuss the key insights from this recent exciting development in Speech AI research. Read more>>
How to use audio data in LangChain with Python: Learn how to integrate audio files seamlessly into LangChain. Develop robust LLM apps leveraging spoken data, all detailed in our step-by-step Python guide. Read more>>
Convert Speech to Text in Python in 5 Minutes: Learn how to perform Automatic Speech Recognition in 5 minutes using Python and the AssemblyAI Speech-to-Text API with this simple tutorial. Read more>>
Our Trending YouTube Tutorials
AutoGen Tutorial 🤖 Create Collaborating AI Agent teams: Discover the power of AutoGen in crafting collaborative AI agent teams. Dive into AutoGen's capabilities and learn to build with it.
Build Talking AI ChatBot with ElevenLabs and OpenAI in 5 Minutes: Learn how to build an AI Audio Bot in Python using ElevenLabs, AssemblyAI & OpenAI.
Retrieval Augmented Generation on audio data with LangChain: Uncover the potential of Retrieval Augmented Generation (RAG) in enhancing LLM responses' relevance and clarity. Learn how to utilize RAG on audio data.
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.