Blog | AssemblyAI

Releases & Updates AI voice agents

Introducing AssemblyAI-TTS-1: text-to-speech built for voice agents Tom Shapland

Releases & Updates AI voice agents

Universal-3.6 Pro Realtime: trained on real conversations, built for real voice agents Ilya Sklyar

Insights & Use Cases Word Error Rate (WER)

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

Insights & Use Cases Speech-to-Text

AssemblyAI Universal-3.5 Pro vs OpenAI Whisper (2026) Patrick Loeber

Releases & Updates AI voice agents

Universal-3.6 Pro Realtime is live Madison Bernstein

Releases & Updates

Introducing AssemblyAI-TTS-1: text-to-speech built for voice agents

AI voice agents

Introducing AssemblyAI-TTS-1: text-to-speech built for voice agents Tom Shapland

Introducing Voice Standard Bench: 50+ models, ranked by performance, speed and cost on real audio

LLM Gateway

Introducing Voice Standard Bench: 50+ models, ranked by performance, speed and cost on real audio Devon Malloy

Abstract blue sphere illustration

AI voice agents

Universal-3.6 Pro Realtime: trained on real conversations, built for real voice agents Ilya Sklyar

Abstract blue sphere illustration

AI voice agents

Universal-3.6 Pro Realtime is live Madison Bernstein

Cheerful computers passing messages and parcels between green hands

Releases & Updates

Universal-3.5 Pro is now on OpenRouter David Lange

Abstract blue levels illustration

Dictation

Introducing our Dictation API Madison Bernstein

Abstract blue levels illustration

LLM Gateway

Introducing Qwen3.5 4B on LLM Gateway—optimized by AssemblyAI for the fast rewrite tasks at the center of voice products

Abstract blue levels illustration

AI voice agents

Introducing the Sync API: Finished Transcripts in a Single API Call Madison Bernstein

Insights & Use Cases

Abstract green diamond illustration

LLM Gateway Best LLM for Transcript Correction in 2026: Fix ASR Errors Without Rewriting What Was Said Kelsey Foster

Abstract green half-sphere illustration

LLM Gateway Best LLMs for Dictation Cleanup: Speed, Quality, and Cost, Benchmarked (2026) Kelsey Foster

Abstract green half-sphere illustration

LLM Gateway Best LLM for Summarizing Transcripts: From 30-Second Voicemails to Hour-Long Meetings Kelsey Foster

Abstract green cylinder illustration

LLM Gateway Best LLMs for Extracting Structured Data from Transcripts (JSON Output, Speed, and Cost) Kelsey Foster

Abstract green diamond illustration

Text-to-speech How to stream text to speech in Python over a WebSocket Kelsey Foster

Abstract green sphere illustration

Text-to-speech Text to speech vs speech to text: what's the difference and how they work together Kelsey Foster

News

Abstract yellow diamond grid illustration

Events

Building voice agents for the real world: 7 takeaways from our NYC meetup with LiveKit Kelsey Foster

Abstract yellow diamond grid illustration

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

Abstract yellow triangle grid illustration

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

Abstract yellow diamond grid illustration

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

Abstract yellow diamond grid illustration

AI voice agents New 2026 insights report: What actually makes a good voice agent Kelsey Foster

Abstract yellow diamond grid illustration

Events Nov. Voice AI meetup recap: Real-world challenges of deploying voice AI agents Maxinne Rillo

Abstract yellow diamond grid illustration

News AssemblyAI Named Leader in G2's Fall 2025 Voice Recognition Grid® Report Devon Malloy

Video

Assembly Required title card: The shift from post-call analysis to live insights, with Kelsey Foster, Growth at AssemblyAI

Conversation Intelligence

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

Assembly Required title card: The ongoing need for human-in-the-loop in conversation intelligence, with Kelsey Foster, Growth at AssemblyAI

Conversation Intelligence

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

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

Video

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

Building with AI in 2025: Top advice from leading founders

Product Management

Building with AI in 2025: Top advice from leading founders Kelsey Foster

AI product strategy in 2025: Top advice from AI-first founders

Video

AI product strategy in 2025: Top advice from AI-first founders Kelsey Foster

Newsletter

Abstract orange cone illustration

SF Hackathon + In-App Playground + 99 Language Support | Newsletter Devon Malloy

Abstract orange sphere illustration

Streaming STT Performance Update | Newsletter Devon Malloy

Abstract orange sphere illustration

Enhanced diarization + Dovetail case study + G2 wins | Newsletter Devon Malloy

Abstract orange sphere illustration

Build Powerful Speech AI Apps with AssemblyAI & Speaker Diarization Tutorials Smitha Kolan

Abstract orange cone illustration

AssemblyAI's C# .NET SDK + Latest Tutorials Smitha Kolan

You may also be interested in

Abstract green diamond illustration

How to stream text to speech in Python over a WebSocket

Abstract green sphere illustration

Text to speech vs speech to text: what's the difference and how they work together

Abstract green sphere illustration

How to evaluate TTS for voice agents