📰 Dev.to · Mart Schweiger

For most of the last decade, transcription was something you did after the fact. You recorded a...

Every healthcare AI team lands on the same question eventually. You want ambient clinical...

You've decided to build a voice product. Maybe it's a support agent, maybe an AI companion, maybe a...

There's a school of voice-agent development that treats turn detection as something you buy, not...

Ask an STT vendor how fast they are and you'll get a word error rate and an average latency number....

You've got a recording and you want text back. For years that meant one thing at AssemblyAI: submit...

Every voice agent does the same three things. It listens, it thinks, and it talks back. The...

Here's a small experiment. Say "user at assembly a-i dot com" out loud and imagine transcribing it...

Most speech-to-text demos use clean audio. One speaker, a good mic, a quiet room. Your production...

A clinical AI pipeline looks deceptively simple on a whiteboard. Audio goes in. A speech-to-text...

AI transcripts often misfire on drug names, dosages, and jargon. Learn to measure accuracy with Missed Entity Rate and the tools that get terms right.

Speaker embeddings are the voice "fingerprints" behind diarization. See how the 4-step pipeline labels who spoke when — with code and accuracy benchmarks.

Audio, metadata, and structural context turn generic speaker labels into named, role-assigned participants. See how to configure each one in the API.

Your voice agent is mid-conversation when Anthropic's API returns a 529 overloaded error. The user is...

Picking an LLM gateway used to be a niche infrastructure decision. In 2026, it's table stakes for any...

A runnable Node.js bridge that places a real outbound phone call with Twilio and bridges its audio into AssemblyAI's Voice Agent API. One WebSocket on each side

Build a multi-user, browser-ready voice agent in Python. LiveKit handles the WebRTC transport — rooms, participants, recording, geographic distribution, mobile

Build a real-time voice agent in Node.js with one WebSocket and one API key. The AssemblyAI Voice Agent API handles the entire conversational pipeline — speech

Voice agents in noisy environments: learn how they work, where they fit, and how to build them for drive-thrus, contact centers, and field teams at scale.

OpenAI Realtime API migration guide: learn how to move to AssemblyAI Voice Agent API with less session code, simpler audio streaming, and tool support.

What Is an AI Voice Agent? Voice agents are software systems that engage in natural speech...

Overview This tutorial demonstrates creating an AI-powered interview evaluation system...

Overview This article examines the real costs of self-hosting OpenAI's Whisper versus...

Overview This tutorial demonstrates creating a complete voice agent that listens, thinks,...