Newsletter

Build Powerful Speech AI Apps with AssemblyAI and LLM Integrations
Build Powerful Speech AI Apps with AssemblyAI and LLM Integrations

Build powerful Speech AI applications with AssemblyAI and learn how to integrate with top platforms like LangChain, LlamaIndex, Twilio, and AWS, and discover new guides on using Large Language Models (LLMs) for querying, summarizing, and generating content.

Get More from Audio Data with Conversational Intelligence
Get More from Audio Data with Conversational Intelligence

With the vast sea of digital conversational data generated daily—from virtual meetings and call centers to chatbots—enterprises are increasingly turning to AI to navigate this information flood. AssemblyAI offers many capabilities to draw the most insights from your audio data.

🎙️ Speaker Diarization Now More Accurate & 🔔 Introducing Billing Alerts
🎙️ Speaker Diarization Now More Accurate & 🔔 Introducing Billing Alerts

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.

🇩🇪 New German STT & Improved PII Detection Models
🇩🇪 New German STT & Improved PII Detection Models

German is now supported in Universal-1, our top multilingual STT model! Transcribe German audio and video with high accuracy. We've also enhanced PII Redaction and Entity Detection, adding 16 new entities and support for Chinese, Dutch, Japanese, and Georgian.

Newsletter #39: Build With AssemblyAI's Integrations
Newsletter #39: Build With AssemblyAI's Integrations

Make the most of your audio data by using AssemblyAI with top platforms and tools. Discover our wide range of integrations to improve your speech AI workflows.

Newsletter #38: Apply LLMs To Voice Data
Newsletter #38: Apply LLMs To Voice Data

Get more from your voice data with our new guides on using Large Language Models (LLMs) with LeMUR. Learn how to ask questions, summarize, extract, and generate content from your audio data.

Newsletter #37: Speaker Diarization Now in 5 New Languages 🇨🇳🇮🇳🇯🇵🇰🇷🇻🇳 & Latest Speech AI tutorials
Newsletter #37: Speaker Diarization Now in 5 New Languages 🇨🇳🇮🇳🇯🇵🇰🇷🇻🇳 & Latest Speech AI tutorials

AssemblyAI's Speaker Diarization model now supports five additional languages: Chinese 🇨🇳, Hindi 🇮🇳, Japanese 🇯🇵, Korean 🇰🇷, and Vietnamese 🇻🇳.

Newsletter #36: Latest Speech-to-text Model Benchmarks
Newsletter #36: Latest Speech-to-text Model Benchmarks

Latest Speech-to-text Model Benchmarks & AssemblyAI JavaScript SDK 4.4.3 Released

Newsletter #35: Nano & Best: New Speech-to-text Pricing Options
Newsletter #35: Nano & Best: New Speech-to-text Pricing Options

Learn about our recently announced Best and Nano tiers, along with a deep dive into the architecture of AssemblyAI in this week's newsletter.

Newsletter #34: AssemblyAI API Reference & Latest Tutorials
Newsletter #34: AssemblyAI API Reference & Latest Tutorials

🚀 Explore our enhanced API docs with a new interactive playground and comprehensive API updates. Try it now! 🔄 Codec support expanded and account deletion feature added. More details in our changelog.

Newsletter #33: Make.com Speech AI Integration and Streaming STT Updates
Newsletter #33: Make.com Speech AI Integration and Streaming STT Updates

Discover how to integrate AssemblyAI with Make.com for seamless Speech AI automation in your workflows. Automate tasks like transcription and PII redaction with ease. Visit our documentation for more details.

Newsletter #32:⚡️Upgrades To Streaming Speech-to-Text
Newsletter #32:⚡️Upgrades To Streaming Speech-to-Text

Track total audio duration in streaming sessions with our new SessionInformation message for precise billing. Also, explore PCI DSS and GDPR compliance achievements to ensure secure and privacy-respecting data handling.

AssemblyAI + 🔗LangChain Go, Universal-1 Recap
AssemblyAI + 🔗LangChain Go, Universal-1 Recap

Explore our new AssemblyAI and LangChain Go integration to unlock powerful LLM capabilities for audio data. Check out Universal-1, our advanced multilingual Speech-to-Text model with unmatched accuracy.

Newsletter #30: 🚀Universal-1 Model Launch
Newsletter #30: 🚀Universal-1 Model Launch

This week, we’ve launched Universal-1, our most powerful and accurate Speech-to-Text model to date, trained on 12.5M hours of multilingual audio data

Build Audio LLM Apps with AssemblyAI
Build Audio LLM Apps with AssemblyAI

Hey 👋, this weekly update contains the latest info on our new product features, tutorials, and our community LeMUR Cookbooks: Build Audio LLM Apps 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

Improved Streaming Speech-to-Text Pricing and Features
Improved Streaming Speech-to-Text Pricing and Features

Streaming Speech-to-Text makes it easier than ever to transcribe live audio and videos. You can also now customize the end-of-utterance detection of Streaming Speech-to-Text for a smoother experience.

🔥 New Free Video Course from Talk Python: Build an Audio AI App
🔥 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 by 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 and LeMUR capabilities.

Improved Audio LLM Docs & AssemblyAI Go SDK
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
AssemblyAI Java SDK New Features & Improvements

We've updated our Java SDK with improved real-time transcription controls, new content safety features, and an additional LLM, Claude 2.1 to LeMUR.

New Utterance Controls for Real-Time Transcription
New Utterance Controls for Real-Time Transcription

Customize the silence threshold for automatic utterance detection and programmatically force the end of an utterance, giving you precise control over when your real-time stream produces a final transcript.

PII Redaction and Entity Detection In 13 New Languages 🇫🇷🇩🇪🇮🇳
PII Redaction and Entity Detection In 13 New Languages 🇫🇷🇩🇪🇮🇳

We've expanded our PII Redaction and Entity Detection to include 13 new languages: Spanish, Finnish, French, German, Hindi, Italian, Korean, Polish, Portuguese, Russian, Turkish, Ukrainian, and Vietnamese.

Improvements to Real-Time Transcription
Improvements to Real-Time Transcription

We're excited to announce some new features to our Python SDK, to improve your experience with building with real-time transcription.

Ask questions about your audio with LLMs
Ask questions about your audio with LLMs

Ask questions about your audio data with LLMs, enabling tasks like summarization and Q&A using AssemblyAI's LeMUR

🚀New AssemblyAI Go SDK & Speech-to-Text Tutorials
🚀New AssemblyAI Go SDK & Speech-to-Text Tutorials

🚀Announcing the AssemblyAI Go SDK & latest Speech-to-text tutorials

Claude 2.1 Now Available with LeMUR + New Integrations
Claude 2.1 Now Available with LeMUR + New Integrations

Claude 2.1 is now available through LeMUR and check out our new Haystack & Semantic Kernel Integration.