🚀Upcoming Q4 Product Updates
We're shipping a lot of new product updates and enhancements before 2023 wraps. Here's a small teaser of a few enhancements that will ship soon:
- GDPR Certification ✅ - Ensuring your data's security and compliance.
- Enhanced Punctuation/Casing - For more accurate transcriptions.
- Reduced latency in Real-time Transcription - Faster response for live interactions.
- LeMUR Speaker Labels Upgrade - Clearer speaker differentiation in transcripts.
We'll have even more to share beyond these updates soon.
AssemblyAI Cookbooks
Easily integrate AssemblyAI into your products with our new resource: The AssemblyAI Cookbook! These cookbooks are a collection of in-depth tutorials for using AssemblyAI beyond the basics of the API.
Check out the following popular cookbooks:
- Core Transcription 🎙️: Transcribing an Audio File
- Audio Intelligence 🤖 : Creating Summarized Chapters from Podcasts
- Real-time 🕒: Using Real-Time Streaming
- LeMUR 🐾 : Leverage LeMUR for Customer Call Sentiment Analysis
Featured News
Stay updated with our latest features, interviews and more on Discord, Twitter and LinkedIn.
- Ably published a tutorial on how to build a real-time closed-caption system in React using AssemblyAI.
- Domenic Donato, AssemblyAI's VP of Technology, was interviewed at Google Cloud Next.
Fresh From Our Blog
Real-time transcription in Python: Learn how to perform real-time transcription on audio streams using Python in this tutorial. 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>>
Introduction to Large Language Models for Generative AI: Understand the mechanics behind Generative AI language models like ChatGPT. Discover how these models are transforming human-AI interaction with this simple guide. Read more>>
Our Trending YouTube Tutorials
Retrieval Augmented Generation on audio data with LangChain: Retrieval Augmented Generation (RAG) is a technique to increase the relevance and transparency of LLM responses. In this tutorial, we'll learn how to perform RAG on audio data using LangChain and Python.
Build Talking AI ChatBot with ElevenLabs and OpenAI in 5 Minutes: Learn how to build a AI Audio Bot in Python using ElevenLabs, AssemblyAI & OpenAI.
Is it really the best 7B model? (A First Look): Mistral claims that the 7.3B parameter model outperforms other models of its size and even bigger. Find out why.
