Speech & Text | Blog from AssemblyAI

Marco Ramponi

Niels Swimberghe

Niels Swimberghe

Kelsey Foster

Ryan O'Connor

Senior Developer Educator

Kelsey Foster

Marco Ramponi

Francis McCann

Marco Ramponi

Kelsey Foster

Ryan O'Connor

Senior Developer Educator

Kelsey Foster

No results found!

Please try different search parameters.

Featured

April 8, 2026

Kelsey Foster

March 24, 2026

Zackary Klebanoff

Applied AI Lead

March 3, 2026

February 3, 2026

Madison Bernstein

Product Marketing

Releases & updates

Kelsey Foster

Madison Bernstein

Product Marketing

Madison Bernstein

Product Marketing

Madison Bernstein

Product Marketing

Insights & use cases

Kelsey Foster

Kelsey Foster

Kelsey Foster

Kelsey Foster

News

Devon Malloy

Staff Growth Manager

Kelsey Foster

Kelsey Foster

Kelsey Foster

Video

Kelsey Foster

Kelsey Foster

Kelsey Foster

Devon Malloy

Staff Growth Manager

Smitha Kolan

Developer Educator

Subscribe to AssemblyAI’s newsletter

Thank you for subscribing!

Oops! Something went wrong while submitting the form.

Unlock the value of voice data

Build what’s next on the platform powering thousands of the industry’s leading of Voice AI apps.

Blog

Why Language Models Became Large Language Models And The Hurdles In Developing LLM-based Applications

How to integrate spoken audio into LangChain.js using AssemblyAI

Introducing the AssemblyAI integration for LangChain.js

Customer Stories: Conformer-2 in Action

How Reinforcement Learning from AI Feedback works

LeMUR: Now Available for Early Access

Recent developments in Generative AI for Audio

Conformer-2: a state-of-the-art speech recognition model trained on 1.1M hours of data

Large Language Models for Product Managers: 5 Things to Know

How AI helps Marvin's users spend 60% less time analyzing research data

Introduction to Large Language Models for Generative AI

3 ways to build and deploy AI tools and features faster

Featured

How to evaluate speech recognition models

Why your word error rate (WER) benchmark might be lying to you

Conversation Intelligence: The complete guide for 2026

Introducing Universal-3 Pro: A new class of speech language model optimized for Voice AI

Releases & updates

Voice AI guardrails: Built-in protection for compliance, quality, and cost control

Introducing Medical Mode: Purpose-built accuracy for medical terminology

Universal-3 Pro Streaming: The most accurate real-time transcription model for voice agents

Introducing Universal-3 Pro: A new class of speech language model optimized for Voice AI

Insights & use cases

Tutorial: How to easily build a voice agent with AssemblyAI

How to build a voice agent with Python in 5 minutes

When to stop self-hosting Whisper (and what you actually gain)

Edge cases in transcription: Offline mode, partial audio files and API limits

News

AssemblyAI Named a Leader in G2’s Spring 2026 Voice Recognition Report

Voice AI in 2026: Inside the companies and investments shaping the future of speech

Inside AssemblyAI's NYC voice agents January 2026 meetup: Production insights from the front lines

New 2026 insights report: What actually makes a good voice agent

Video

Real-time conversation intelligence: The shift from post-call analysis to live insights

The ongoing need for human-in-the-loop in conversation intelligence

Predicting the future: What top AI founders have to say about innovation in 2025

Building with AI in 2025: Top advice from leading founders

Newsletter

SF Hackathon + In-App Playground + 99 Language Support | August 29, 2025 Newsletter

Streaming STT Performance Update | August 1, 2025 Newsletter

Enhanced diarization + Dovetail case study + G2 wins | July 18, 2025 Newsletter

Build Powerful Speech AI Apps with AssemblyAI & Speaker Diarization Tutorials

Unlock the value of voice data