This is the 6th launch from AssemblyAI. View more

Universal-Streaming

Ultra-fast, ultra-accurate streaming STT for voice agents.

Universal-Streaming delivers all the streaming speech-to-text voice agents need in one robust API: ultra-fast immutable transcripts, higher accuracy, built-in endpointing, and transparent pricing at $0.15/hour with unlimited concurrency.

Free

Launch tags:

API•Developer Tools•Artificial Intelligence

Launch Team

Devon Malloy

AssemblyAI

Maker

📌

Six months ago, we launched Universal-2 to tackle last-mile accuracy in speech recognition—today, we’re excited to introduce Universal-Streaming, our purpose-built, real-time speech-to-text model designed specifically for voice agents. Universal-Streaming isn’t just fast—it’s a game-changer for real-time apps: ⚡ ~300ms immutable transcripts with no partial/final tradeoff 🧠 Intelligent endpointing that smooths out awkward pauses and interruptions 🔒 Accurate on the tokens that matter—emails, codes, names 🌎 Unlimited concurrency at just $0.15/hr with no surprise fees And it’s not just about the benchmarks—developers building real-world voice agents are already seeing the difference: more natural interactions, higher task completion, and easier scaling from 5 to 50,000+ concurrent users. Whether you're shipping AI assistants, realtime transcription tools, or something entirely new—Universal-Streaming gives you the power to build voice products your users will actually love to talk to. We can’t wait to see what you build—try it out and tell us what you think!

Report

21d ago

Alex Redfern

LanguaTalk

@devon_malloy congrats on the launch. Couple of Qs: 1) which languages does it support? 2) do you have benchmark data by language vs 11labs Scribe and Deepgram Nova-3? Couldn't find answers to either.

Report

8d ago

Marat Zainullin

Hey, AssemblyAI Team,
I’ve been working on a fully offline, on-device streaming ASR engine for iOS.
Would love to get feedback or benchmark ideas!

If anyone's curious to try it on their device, I’m happy to add you to TestFlight — just DM me.
https://github.com/make1986/ios-streaming-asr-offline

Report

8d ago

AssemblyAI Launches

Universal-Streaming Ultra-fast, ultra-accurate streaming STT for voice agents.

Launched on June 3rd, 2025

Universal 2 Speech-to-text for conversational data

Launched on October 31st, 2024

Universal-1 Multilingual speech AI model trained on 12.5M hours of data

Launched on May 21st, 2024

View all AssemblyAI launches

Do you use AssemblyAI?

Review AssemblyAI?

4.44/5 based on 19 reviews

View all reviews

Maker reviews of AssemblyAI

Susan Pan

used this to build Inkr 2.0

Inkr – Instant & Accurate Transcriptions

(795 points)

What sets AssemblyAI apart is its simplicity and seamless integration for transforming speech into meaningful text. Their API is easy to implement, providing highly accurate and fast transcription with industry-leading accuracy, while also offering features like sentiment analysis and content moderation out of the box.

Report

1mo ago

Elissa Craig

used this to build TL;DL (Beta) by Headliner

Headliner

(164 points)

Headliner uses AssemblyAI to help power our transcription capabilities. Transcription helps inform our audio summaries.

Report

2mo ago

Felix Tao

used this to build Me.bot

Me.bot

(2,367 points)

AssemblyAI offers an advanced, easy-to-integrate speech recognition API that excels in transcribing audio data accurately. It supports a range of media types! Super handy to use.

Report

11mo ago

View all AssemblyAI reviews

Reviews of AssemblyAI

Blair

ChatPDF

Launching soon!

•2 reviews

I've just given the API a try with Make. The documentation is superb and the outcomes are of top-notch quality.

Report

5mo ago

Xbei lu

•2 reviews

The precision was impressive, yet it was the comprehensive documentation and distinctive features such as Auto Chapters and Sentiment Analysis that truly swayed us.

Report

6mo ago