Newsletter #30: šUniversal-1 Model Launch
This week, weāve launchedĀ Universal-1, our most powerful and accurate Speech-to-Text model to date, trained on 12.5M hours of multilingual audio data
Smitha Kolan
Smitha Kolan is a Developer Educator at AssemblyAI, a AI/ML YouTuber & Educator at SchoolOfMachineLearning.com.
Build Audio LLM Apps with AssemblyAI
Hey š, this weekly update contains the latest info on our new product features, tutorials, and our community LeMUR Cookbooks: Build Audio LLM Apps LeMURĀ is the easiest way to code applications that apply LLMs to speech. In just a few lines of code, you canĀ search,Ā summarize,Ā ask questions, and
š„ New Free Video Course from Talk Python: Build an Audio AI App
We're thrilled to announce that the in-depth 4+ hour video course created byĀ Talk Python, "Build An Audio AI App", is now available! In this hands-on course, you'll learn how to build a real-world app working with podcast audio using AssemblyAI's speech-to-text andĀ LeMURĀ capabilities.
Improved Audio LLM Docs & AssemblyAI Go SDK
Build with audio data and LLMs using LeMUR - revamped docs with prompt guides, 4 key use cases. AssemblyAI's Go SDK v1.2.0 adds transcript word search and LeMUR data purging.
AssemblyAI Java SDK New Features & Improvements
We've updated ourĀ Java SDKĀ with improved real-time transcription controls, new content safety features, and an additional LLM, Claude 2.1 toĀ LeMUR.