AssemblyAI

Transform speech into meaning with one robust API

5K followers

Build new AI products with voice data leveraging AssemblyAI’s industry-leading Speech AI models for accurate speech-to-text, speaker detection, sentiment analysis, chapter detection, PII redaction, and more. Join 5,000+ industry-leading companies—including Fireflies.ai, Glean, and Loop—unlocking the power of voice data and launching best-in-class products and experiences.

Blog

•

Newsletter

•

Questions

•

Forums

•

Product Categories

•

Apps

•

About

•

Terms

•

Privacy and Cookies

•

X.com

•

Facebook

•

Instagram

•

YouTube

•

Advertise

This is the 5th launch from AssemblyAI. View more

Universal 2

Speech-to-text for conversational data

Introducing Universal-2: The latest advancement in Speech-to-Text technology. Capture the complexity of human speech, enhanced transcript quality, and better conversational insights by tapping into the next generation of Speech AI.

Free Options

Launch tags:

API•Developer Tools•Artificial Intelligence

Launch Team

Nick Morris

AssemblyAI

Maker

📌

Five months ago, we introduced Universal-1, our best-in-class Speech-to-Text model that achieved remarkable robustness and accuracy across several industry-critical benchmarks. Today, we're launching Universal-2, which builds upon that foundation to address critical "last-mile" challenges in conversational data. Universal-2 pushes the boundaries of Speech-to-Text technology by improving accuracy in areas that matter most for real-world applications: ⭐️ 24% improvement in the recognition of names, brands, locations, and more ⭐️ 21% increase in accuracy across critical data like phone numbers, zip codes, and other numerical identifiers ⭐️ 15% improvement in transcript structure with proper punctuation and casing for things like emails, dates, and dollar amounts And most importantly, nearly 3/4s of users prefer Universal-2 over other Speech AI models. Universal-2 bridges the gap between raw accuracy metrics and what makes transcripts truly useful—precise formatting, accurate proper nouns, and natural-looking output that businesses can trust. Try it out and let us know what you're building with it!

Report

7mo ago

AnnaHo

Picture Picker—Collect,Create,Edit Image

@nick_morris4 Universal-2 is an impressive leap forward in Speech-to-Text technology, capturing the nuances of human speech with remarkable accuracy!

Report

7mo ago

Samuel Bissegger

Univerbal

Congratulations on the launch, @nick_morris4 and Team! Very cool name as well😉. STT model will only gain importance, and quality might be the main differentiator. Keep up the great work!

Report

7mo ago

Zack Louw

I like anything speech to *****. It applies to so many industries and use cases. I have seen this come in handy especially in the medical space where there is a ton of data capture happening off the back of human interaction.

Report

4mo ago

AssemblyAI

Transform speech into meaning with one robust API

AssemblyAI Launches

Do you use AssemblyAI?

Review AssemblyAI?

Maker reviews of AssemblyAI

Reviews of AssemblyAI

Universal 2