Streaming Speech-to-Text
Abstract green cylinder illustration
September 30, 2026

How to build the lowest latency voice agent in Vapi: Achieving ~465ms end-to-end Latency

By 
Daniel Ince
, 
Product
Insights & Use Cases
Abstract green cylinder illustration
September 30, 2026

Top APIs and models for real-time speech recognition and transcription in 2026

By 
Kelsey Foster
, 
Growth
Insights & Use Cases
Abstract green half-sphere illustration
October 13, 2026

8 best voice agent orchestration tools in 2026: open-source and managed

By 
Jesse Sumrak
, 
Featured writer
Insights & Use Cases
Abstract blue levels illustration
June 2, 2025

Introducing Universal-Streaming: Ultra-Fast, Ultra-Accurate Speech-to-Text for Voice Agents

By 
JD Prater
, 
Head of Product Marketing
Releases & Updates
Abstract green cone illustration
September 30, 2026

Build an AI Voice Agent with DeepSeek R1, AssemblyAI, and ElevenLabs

By 
Smitha Kolan
, 
Developer Educator
Insights & Use Cases
August 25, 2026

Biggest challenges in building AI voice agents (and how AssemblyAI & Vapi are solving them)

By 
Smitha Kolan
, 
Developer Educator
Insights & Use Cases
Abstract blue sphere illustration
March 5, 2025

Raising the bar for Speech AI: Announcing a first of its kind Speech Language Model and improved Streaming model

By 
Dylan Fox
, 
Founder, CEO
Releases & Updates
Abstract green cylinder illustration
June 5, 2025

How to build a LiveKit AI Agent for real-time Speech-to-Text

By 
Ryan O'Connor
, 
Senior Developer Educator
Insights & Use Cases
Subscribe to 
AssemblyAI’s newsletter
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.