Home / Companies / AssemblyAI / Blog

AssemblyAI Blog

798 posts indexed since 2022

Blog URL
Posts YTD
300 ↑ vs 127 last year
Avg Posts/Month
13.3 since 2022
Monthly Post Volume
Monthly post counts
MonthPosts
1-202217
2-202217
3-202214
4-20226
5-20223
6-202210
7-20225
8-20229
9-202211
10-20222
11-20224
12-20228
1-20233
2-20232
3-20234
4-20233
5-202310
6-20233
7-20233
8-202312
9-202316
10-202313
11-202316
12-202312
1-202415
2-202412
3-202412
4-202418
5-202413
6-202413
7-202411
8-202417
9-202414
10-202413
11-202412
12-202410
1-20255
2-202516
3-202515
4-20258
5-20255
6-20257
7-202516
8-202518
9-202511
10-202515
11-202511
12-20258
1-20268
2-202625
3-202626
4-202644
5-202640
6-202628
7-202629
8-202636
9-202625
10-202639
11-20260
Post Details

798 matching posts

Title Author Published Words HN Pts
Build smarter voice agents: 7 takeaways from our July 23rd San Francisco meetup Maxinne Rillo 2026-07-30 1,890 --
Independently verified: Universal-3.5 Pro on the public speech-to-text benchmarks -- 2026-07-25 1,631 --
AssemblyAI's Universal-3.5 Pro Realtime is the only model in Coval's Human Parity Zone Kelsey Foster 2026-07-25 1,699 --
Best voice agent API for startups building their first voice product Kelsey Foster 2026-07-23 2,931 --
How to transcribe audio from a mobile app (iOS/Swift, Android/Kotlin, React Native) Kelsey Foster 2026-07-23 2,886 --
Why real-time is the future of speech-to-text Kelsey Foster 2026-07-23 2,841 --
Transcription webhooks and callbacks: get notified when a transcript is ready Kelsey Foster 2026-07-23 2,428 --
Speech-to-text API fundamentals: authenticate, poll status, and parse the JSON response Kelsey Foster 2026-07-23 2,587 --
AI medical scribe: build vs buy against Nuance DAX and Abridge Kelsey Foster 2026-07-23 2,635 --
DER vs. cpWER: why the standard diarization metric ranks systems backwards Gabriel Oexle 2026-07-21 248 --
Node.js voice agent with AssemblyAI Universal-3.5 Pro Realtime Kelsey Foster 2026-07-21 1,335 --
Vapi voice agent with AssemblyAI Universal-3.5 Pro Realtime Kelsey Foster 2026-07-21 1,211 --
Twilio phone agent with AssemblyAI Universal-3.5 Pro Realtime Kelsey Foster 2026-07-21 1,202 --
Pipecat voice agent with AssemblyAI Universal-3.5 Pro Realtime Kelsey Foster 2026-07-21 1,483 --
How to catch voice agent regressions before your users do Griffin Sharp 2026-07-18 1,421 --
Fast ASR for voice agents: bring your own turn detection Kelsey Foster 2026-07-16 1,836 --
Build a dictation app with the Sync API Kelsey Foster 2026-07-16 2,634 --
Bring your own orchestration: the sync HTTP pattern for voice agents Kelsey Foster 2026-07-16 1,923 --
Sync vs. async transcription: which to use and how fast each can go Kelsey Foster 2026-07-16 1,955 --
Time to first token: the latency metric that decides voice agents Kelsey Foster 2026-07-16 2,271 --
Introducing the Sync API: transcripts in a single call -- 2026-07-15 1,333 --
What is conversation context in voice AI — and why it improves accuracy Kelsey Foster 2026-07-09 1,625 --
Voice agent architectures explained: STT→LLM→TTS vs. speech-to-speech vs. one API Kelsey Foster 2026-07-09 1,961 --
How to build a voice agent that transfers to a human Kelsey Foster 2026-07-09 2,127 --
Which voice agent API has the best developer experience? What to evaluate Kelsey Foster 2026-07-09 1,874 --
AssemblyAI vs. Deepgram for batch transcription: accuracy, turnaround, and pricing Kelsey Foster 2026-07-09 1,700 --
Async transcription accuracy on hard audio: noisy call centers, overlapping speakers, and filler words Kelsey Foster 2026-07-09 1,904 --
Universal-3.5 Pro: native code switching, our most accurate speaker diarization yet, and expanded language support -- 2026-07-07 1,777 --
Contextual Awareness in Universal-3.5 Pro Realtime Zackary Klebanoff 2026-07-02 1,339 --
Batch transcription at scale: turnaround, throughput, and concurrency Kelsey Foster 2026-06-30 1,672 --
Transcribing heavy accents: why ASR struggles, and how model scale helps Kelsey Foster 2026-06-30 1,690 --
What languages does the Voice Agent API support? Kelsey Foster 2026-06-30 1,252 --
Analyzing and scoring voice agent calls with the LLM Gateway Kelsey Foster 2026-06-30 1,707 --
Wrong drug name in, wrong SOAP note out: error propagation in clinical AI pipelines Kelsey Foster 2026-06-24 1,808 --
Veterinary transcription API: handling species, breeds, and vet drug names Kelsey Foster 2026-06-24 1,729 --
Medical transcription in Spanish, German, and French: multilingual clinical accuracy Kelsey Foster 2026-06-24 1,759 --
Real-time STT latency benchmarks: what "fast enough" means for voice agents Kelsey Foster 2026-06-24 2,204 --
How we measure medical transcription: MER, and why WER lies to you Kelsey Foster 2026-06-24 1,541 --
Keyterm prompting for real-time accuracy: boosting names, jargon, and product terms Kelsey Foster 2026-06-24 2,312 --
Building behavioral health documentation that clinicians trust Kelsey Foster 2026-06-24 1,837 --
Why streaming transcription drifts to English on multilingual audio — and how to fix language steering Kelsey Foster 2026-06-24 2,206 --
Prompting Claude to build voice agents Kelsey Foster 2026-06-24 2,851 --
One parameter, 20% fewer missed entities: a before/after tour of Medical Mode Kelsey Foster 2026-06-24 1,515 --
Build a voice agent without Pipecat or LiveKit Kelsey Foster 2026-06-24 3,720 --
Universal-3.5 Pro Realtime: the first streaming STT model that takes the agent's question as input -- 2026-06-23 1,663 2
What is speech-to-speech for voice agents? Kelsey Foster 2026-06-16 2,971 --
Best platforms for enterprise voice agents Kelsey Foster 2026-06-16 3,002 --
AssemblyAI vs Deepgram for voice agents Kelsey Foster 2026-06-16 3,291 --
How to build a voice agent for IT helpdesk and technical support Kelsey Foster 2026-06-10 5,092 --
One stream, two jobs: introducing SpeakerRevision Madison Bernstein 2026-06-10 982 --
Plushcap, by Matt Makai. 2021-2026.