Hey ๐, this weekly update contains the latest info on our new product features, tutorials, and our community.
๐๏ธ Speaker Diarization Now More Accurate and Available in 5 More Languages
AssemblyAI's Speaker Diarization service is now more accurate. With the latest upgrades to our model, Speaker Diarization is up to 13% more accurate than its predecessor and achieves the best score in identifying the correct number of speakers compared to other providers.
With this latest update, AssemblyAI's Speaker Diarization is now available in 16 languages. The 5 new languages rolled out are:
- ๐จ๐ณ Chinese
- ๐ฎ๐ณ Hindi
- ๐ฏ๐ต Japanese
- ๐ฐ๐ท Korean
- ๐ป๐ณ Vietnamese
Get Started:
Speaker diarization increases the readability of transcripts and powers a wide range of downstream features in end-user applications, like automated video clipping, call coaching, and automated dubbing.
To start using Speaker Diarization in your applications, check out these guides:
- Getting Started Guide: A comprehensive introduction to using our API.
- Speaker Diarization Docs: A guide for all the ways to use Speaker Diarization, provided in five different programming languages.
- Integration Tutorials: Step-by-step tutorials for integrating AssemblyAI's STT model with various tools like LangChain, Twilio with which you can use the Speaker Diarization model.
Join the Conversation
Weโre excited to see what you build with the upgraded Speaker Diarization model. Share your projects and join the conversation on X.com with the hashtag #AssemblyAI and mention us @AssemblyAI.
๐ Manage Your spend with Billing Alerts
This week, we introduced billing alerts, a new feature on the AssemblyAI dashboard to help you proactively manage your spend. Set up your balance threshold in your billing dashboard with ease and receive an email notification when your balance reaches the threshold.
๐ In case you missed it
Universal-1 now supports German
With the latest addition of German language support to Universal-1, you can now transcribe English, Spanish and German with unmatched accuracy and lightning speed. You can get your AssemblyAI API key and start transcribing today.
Improved PII and Entity Detection models
We've improved our English model for PII Text Redaction and Entity Detection, increasing accuracy in detecting and removing personally identifiable information and other entities from transcripts.
Fresh From Our Blog
How to Create SRT Files for Videos in Node.js: SRT is a widely used and supported format for subtitles in videos. SRT files are very easy to generate with AssemblyAI. Learn how to create SRT subtitle files using Node.js in this easy-to-follow guide. Read more>>
10 Ways Live Transcription is Being Used Today: Streaming Speech-to-Text technology converts real-time audio streams into accurate text. Read how streaming speech-to-text is used across different industries to make interactions more engaging and accessible. Read more>>
Announcing the AssemblyAI Starter App for Encore: If you're curious about using AssemblyAI in a production-like environment, this tutorial is for you! In this tutorial, you'll learn how to deploy a ready-made Speech AI application to the cloud using Encore and the new AssemblyAI starter app for Go. Read more>>
Our Trending YouTube Tutorials
Build An AI ChatBot In Java | Real-Time Prompting: Build an interactive chatbot that can understand and respond to text-to-spoken queries in real time by integrating advanced large language models like Claude.
Build an AI Lecture Assistant with Python: Create an application that summarizes long speeches (e.g.: university lectures, TED Talks or State of the Union), and lets you ask questions with responses that relate specifically to the speech's content.
Apply LLMs on Audio that has Multiple Speakers: LLMs lose valuable information when applied to transcriptions of audio recordings when there are multiple speakers. Learn how to circumvent this problem by using Speaker Diarization.
