Insights & Use Cases

September 9, 2026

Voice AI observability: What to instrument once the agent is live

By

Kelsey Foster

,

Growth

September 9, 2026

How to load test a voice agent before you launch

By

Kelsey Foster

,

Growth

September 2, 2026

Voice coding: how developers dictate to Claude Code, Cursor, and Copilot

By

Kelsey Foster

,

Growth

September 2, 2026

Inside dictation cleanup: How raw speech becomes finished text

By

Kelsey Foster

,

Growth

September 2, 2026

Dictation features: What product teams are shipping in 2026

By

Kelsey Foster

,

Growth

August 26, 2026

Prompt engineering 101: a crash course for 2026

By

Kelsey Foster

,

Growth

August 26, 2026

How to analyze a call recording with AI (no code required)

By

Kelsey Foster

,

Growth

August 26, 2026

Best Python audio processing libraries in 2026 (and when to use a speech-to-text API)

By

Kelsey Foster

,

Growth

August 26, 2026

How to build an AI voice translator in Python

By

Kelsey Foster

,

Growth

August 26, 2026

How to apply LLMs to multi-speaker audio recordings

By

Kelsey Foster

,

Growth

August 26, 2026

Hugging Face Transformers tutorial: pipeline, tokenizer, and models in 2026

By

Kelsey Foster

,

Growth

August 26, 2026

How to learn machine learning in 2026: an updated roadmap

By

Kelsey Foster

,

Growth

August 26, 2026

What are word embeddings? From Word2Vec to modern embedding models

By

Kelsey Foster

,

Growth

August 26, 2026

PyTorch crash course: tensors, autograd, and your first training loop

By

Kelsey Foster

,

Growth

August 26, 2026

How to add voice-note transcription to your app

By

Kelsey Foster

,

Growth

August 26, 2026

How to build push-to-talk dictation with the Sync API

By

Kelsey Foster

,

Growth

August 26, 2026

What is a dictation API? How voice-to-text input actually works

By

Kelsey Foster

,

Growth

August 19, 2026

Universal-3.5 Pro for pre-recorded audio: code-switching and contextual prompting in action

By

Kelsey Foster

,

Growth

August 19, 2026

Sync Speech-to-Text API: a technical walkthrough of one-request transcription

By

Kelsey Foster

,

Growth

August 19, 2026

What it takes to build smarter voice agents: lessons from Retell and Super

By

Kelsey Foster

,

Growth

August 19, 2026

Build an AI medical note-taker with one API

By

Kelsey Foster

,

Growth

August 19, 2026

Entity accuracy in speech-to-text: why word accuracy isn't enough

By

Kelsey Foster

,

Growth

August 19, 2026

Best voice agent API for contact centers: How to choose in 2026

By

Kelsey Foster

,

Growth

August 12, 2026

Agent Context Carryover: more accurate voice agent transcription on LiveKit

By

Martin Schweiger

,

Technical Product Marketing Manager

August 12, 2026

OpenAI Realtime API alternatives in 2026 (and how to migrate)

By

Kelsey Foster

,

Growth

August 12, 2026

Best voice agent API in 2026: how to choose your STT foundation

By

Kelsey Foster

,

Growth

August 12, 2026

The hard cases in speaker diarization: overlap, short turns, and noise

By

Kelsey Foster

,

Growth

August 12, 2026

Does Whisper do speaker diarization? Whisper + pyannote, and its limits

By

Kelsey Foster

,

Growth

August 12, 2026

How to measure speaker diarization accuracy (cpWER) in Python

By

Kelsey Foster

,

Growth

August 4, 2026

AssemblyAI vs self-hosting on Baseten, Modal, or Fireworks

By

Kelsey Foster

,

Growth

August 4, 2026

AssemblyAI vs NVIDIA Parakeet and Canary: Choosing speech-to-text for production

By

Kelsey Foster

,

Growth

August 4, 2026

AssemblyAI vs Qwen3-ASR: picking speech-to-text for production

By

Kelsey Foster

,

Growth

August 4, 2026

AssemblyAI vs Whisper Large-v3: Which speech-to-text should you ship?

By

Kelsey Foster

,

Growth

August 4, 2026

The real cost of self-hosting open-source speech-to-text

By

Kelsey Foster

,

Growth

August 4, 2026

How to build real-time agent assist on streaming speech-to-text

By

Kelsey Foster

,

Growth

August 4, 2026

How to build an AI scribe for therapy sessions that writes progress notes

By

Kelsey Foster

,

Growth

August 4, 2026

Which voice agent platform has the best developer experience?

By

Kelsey Foster

,

Growth

July 29, 2026

Build smarter voice agents: 7 takeaways from our July 23rd San Francisco meetup

By

Maxinne Rillo

,

Senior Field & Campaign Marketing Manager

July 24, 2026

AssemblyAI's Universal-3.5 Pro Realtime is the only model in Coval's Human Parity Zone

By

Kelsey Foster

,

Growth

July 22, 2026

Speech-to-text API fundamentals: authenticate, poll status, and parse the JSON response

By

Kelsey Foster

,

Growth

July 22, 2026

Transcription webhooks and callbacks: get notified when a transcript is ready

By

Kelsey Foster

,

Growth

July 22, 2026

How to transcribe audio from a mobile app (iOS/Swift, Android/Kotlin, React Native)

By

Kelsey Foster

,

Growth

July 22, 2026

Why real-time is the future of speech-to-text

By

Kelsey Foster

,

Growth

July 22, 2026

AI medical scribe: build vs buy against Nuance DAX and Abridge

By

Kelsey Foster

,

Growth

July 22, 2026

Best voice agent API for startups building their first voice product

By

Kelsey Foster

,

Growth

August 25, 2026

5 Lessons from building a voice AI prescription agent

By

Stefan Blos

,

Developer Advocate at Stream

DER vs. cpWER: why the standard diarization metric ranks systems backwards

By

Gabriel Oexle

,

July 17, 2026

How to catch voice agent regressions before your users do

By

Griffin Sharp

,

Applied AI Engineer

July 15, 2026

Fast ASR for voice agents: bring your own turn detection

By

Kelsey Foster

,

Growth

July 15, 2026

Build a dictation app with the Sync API

By

Kelsey Foster

,

Growth

July 15, 2026

Time to first token: the latency metric that decides voice agents

By

Kelsey Foster

,

Growth

July 15, 2026

Bring your own orchestration: the sync HTTP pattern for voice agents

By

Kelsey Foster

,

Growth

July 15, 2026

Sync vs. async transcription: which to use and how fast each can go

By

Kelsey Foster

,

Growth

July 8, 2026

How to build a voice agent that transfers to a human

By

Kelsey Foster

,

Growth

July 8, 2026

What is conversation context in voice AI — and why it improves accuracy

By

Kelsey Foster

,

Growth

July 8, 2026

Which voice agent API has the best developer experience? What to evaluate

By

Kelsey Foster

,

Growth

July 8, 2026

Voice agent architectures explained: STT→LLM→TTS vs. speech-to-speech vs. one API

By

Kelsey Foster

,

Growth

July 8, 2026

AssemblyAI vs. Deepgram for batch transcription: accuracy, turnaround, and pricing

By

Kelsey Foster

,

Growth

July 8, 2026

Async transcription accuracy on hard audio: noisy call centers, overlapping speakers, and filler words

By

Kelsey Foster

,

Growth

June 29, 2026

Analyzing and scoring voice agent calls with the LLM Gateway

By

Kelsey Foster

,

Growth

June 29, 2026

Batch transcription at scale: turnaround, throughput, and concurrency

By

Kelsey Foster

,

Growth

June 29, 2026

Transcribing heavy accents: why ASR struggles, and how model scale helps

By

Kelsey Foster

,

Growth

August 25, 2026

Medical transcription in Spanish, German, and French: multilingual clinical accuracy

By

Kelsey Foster

,

Growth

August 31, 2026

Building behavioral health documentation that clinicians trust

By

Kelsey Foster

,

Growth

June 23, 2026

Veterinary transcription API: handling species, breeds, and vet drug names

By

Kelsey Foster

,

Growth

June 23, 2026

Wrong drug name in, wrong SOAP note out: error propagation in clinical AI pipelines

By

Kelsey Foster

,

Growth

August 31, 2026

How we measure medical transcription: MER, and why WER lies to you

By

Kelsey Foster

,

Growth

August 31, 2026

One parameter, 20% fewer missed entities: a before/after tour of Medical Mode

By

Kelsey Foster

,

Growth

June 23, 2026

Prompting Claude to build voice agents

By

Kelsey Foster

,

Growth

June 23, 2026

Build a voice agent without Pipecat or LiveKit

By

Kelsey Foster

,

Growth

June 23, 2026

Real-time STT latency benchmarks: what "fast enough" means for voice agents

By

Kelsey Foster

,

Growth

June 23, 2026

Keyterm prompting for real-time accuracy: boosting names, jargon, and product terms

By

Kelsey Foster

,

Growth

June 23, 2026

Why streaming transcription drifts to English on multilingual audio — and how to fix language steering

By

Kelsey Foster

,

Growth

August 11, 2026

AssemblyAI vs Deepgram for voice agents

By

Kelsey Foster

,

Growth

August 21, 2026

Speech-to-speech voice agents: how the architecture works

By

Kelsey Foster

,

Growth

August 25, 2026

Best platforms for enterprise voice agents

By

Kelsey Foster

,

Growth

June 9, 2026

How to build a voice agent for IT helpdesk and technical support

By

Kelsey Foster

,

Growth

June 9, 2026

What are conversation analytics (and how to use them with AssemblyAI)

By

Kelsey Foster

,

Growth

June 9, 2026

How does context influence automatic speaker labeling?

By

Kelsey Foster

,

Growth

June 9, 2026

How is speaker embedding used in voice recognition for transcripts?

By

Kelsey Foster

,

Growth

August 31, 2026

How accurate are AI transcripts for technical or medical terms?

By

Kelsey Foster

,

Growth

June 2, 2026

The true cost of inaccurate transcription: why the cheapest API is rarely the cheapest option

By

Kelsey Foster

,

Growth

August 25, 2026

Transcription accuracy vs. transcription quality: why the gap matters

By

Kelsey Foster

,

Growth

August 11, 2026

How to build with the Voice Agent API

By

Kelsey Foster

,

Growth

August 4, 2026

How I built a voice agent without writing (or understanding) any code

By

Devon Malloy

,

Staff Growth Manager

August 25, 2026

Why AssemblyAI's Voice Agent API is designed for coding agents

By

Devon Malloy

,

Staff Growth Manager

May 21, 2026

Building a voice agent with a coding agent: why this approach beats a visual builder

By

Devon Malloy

,

Staff Growth Manager

August 11, 2026

The production ceiling: where voice agent stacks start showing their limits

By

Ryan Seams

,

VP, Customer Solutions

September 8, 2026

The voice agent accuracy problem nobody benchmarks

By

Devon Malloy

,

Staff Growth Manager

May 19, 2026

How the Voice Agent API pipeline works, from audio in to audio out

By

Devon Malloy

,

Staff Growth Manager

September 8, 2026

Using the Voice Agent API alongside an existing voice stack

By

Devon Malloy

,

Staff Growth Manager

August 31, 2026

Build a voice agent for telehealth triage

By

Kelsey Foster

,

Growth

September 1, 2026

How to build a multilingual voice agent with the Voice Agent API

By

Kelsey Foster

,

Growth

May 19, 2026

How to create an AI cold-calling agent with the Voice Agent API

By

Kelsey Foster

,

Growth

July 21, 2026

Build a real-time voice AI agent in Python with the AssemblyAI Voice Agent API

By

Kelsey Foster

,

Growth

May 19, 2026

Build an AI voice agent for customer support that can look up orders

By

Kelsey Foster

,

Growth

May 19, 2026

How to build a voice agent with Twilio and AssemblyAI

By

Kelsey Foster

,

Growth

July 8, 2026

Best API for building a speech-to-speech voice agent in 2026

By

Kelsey Foster

,

Growth

August 31, 2026

How to build an AI scribe for therapy sessions

By

Kelsey Foster

,

Growth

August 25, 2026

Building a voice-powered e-commerce shopping assistant

By

Kelsey Foster

,

Growth