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
MacWhisper vs. Superwhisper vs. Blurt: local models, hybrid apps, and a hosted dictation API Kelsey Foster 2026-09-24 2,766 --
Universal-3.5 Pro is now on OpenRouter -- 2026-09-23 1,313 --
Sync API or Dictation API? How to pick for your dictation feature Kelsey Foster 2026-09-17 3,381 --
Dictation API vs speech-to-text + an LLM: should you buy the bundle or build it? Kelsey Foster 2026-09-17 3,341 --
How to evaluate a dictation API in 2026 Kelsey Foster 2026-09-17 5,780 --
Building voice agents for the real world: 7 takeaways from our NYC meetup with LiveKit Kelsey Foster 2026-09-16 3,081 --
Best dictation APIs for developers in 2026 Kelsey Foster 2026-09-16 3,733 --
How to build clinical dictation on AssemblyAI Kelsey Foster 2026-09-16 3,218 --
Introducing the Dictation API: the first API built for dictation -- 2026-09-16 2,049 --
How to load test a voice agent before you launch Kelsey Foster 2026-09-09 4,541 --
Voice AI observability: What to instrument once the agent is live Kelsey Foster 2026-09-09 3,780 --
Voice coding: how developers dictate to Claude Code, Cursor, and Copilot Kelsey Foster 2026-09-03 2,304 --
Inside dictation cleanup: How raw speech becomes finished text Kelsey Foster 2026-09-03 3,333 --
Dictation features: What product teams are shipping in 2026 Kelsey Foster 2026-09-03 3,113 --
Hugging Face Transformers tutorial: pipeline, tokenizer, and models in 2026 Kelsey Foster 2026-08-27 3,350 --
Prompt engineering 101: a crash course for 2026 Kelsey Foster 2026-08-27 3,761 --
What are word embeddings? From Word2Vec to modern embedding models Kelsey Foster 2026-08-27 5,203 --
How to add voice-note transcription to your app Kelsey Foster 2026-08-27 2,123 --
How to apply LLMs to multi-speaker audio recordings Kelsey Foster 2026-08-27 3,595 --
What is a vector database? Embeddings, indexes, and RAG over audio transcripts -- 2026-08-27 3,569 --
How to build an AI voice translator in Python Kelsey Foster 2026-08-27 3,377 --
Best Python audio processing libraries in 2026 (and when to use a speech-to-text API) Kelsey Foster 2026-08-27 3,412 --
PyTorch crash course: tensors, autograd, and your first training loop Kelsey Foster 2026-08-27 5,054 --
How to learn machine learning in 2026: an updated roadmap Kelsey Foster 2026-08-27 3,943 --
How to analyze a call recording with AI (no code required) Kelsey Foster 2026-08-27 2,771 --
Introducing Qwen3.5 4B on LLM Gateway—optimized by AssemblyAI for the fast rewrite tasks at the center of voice products -- 2026-08-26 1,772 --
5 Lessons from building a voice AI prescription agent Stefan Blos 2026-08-26 2,341 --
The Thinker and the Responder: Bring your own response generation to a voice agent -- 2026-08-26 4,508 --
Universal-3.5 Pro Realtime is now available in Vapi -- 2026-08-26 1,209 --
Best voice agent API for contact centers: How to choose in 2026 Kelsey Foster 2026-08-20 2,405 --
Universal-3.5 Pro for pre-recorded audio: code-switching and contextual prompting in action Kelsey Foster 2026-08-20 1,145 --
Build an AI medical note-taker with one API Kelsey Foster 2026-08-20 1,780 --
Sync Speech-to-Text API: a technical walkthrough of one-request transcription Kelsey Foster 2026-08-20 1,331 --
What it takes to build smarter voice agents: lessons from Retell and Super Kelsey Foster 2026-08-20 2,040 --
Entity accuracy in speech-to-text: why word accuracy isn't enough Kelsey Foster 2026-08-20 2,465 --
How to measure speaker diarization accuracy (cpWER) in Python Kelsey Foster 2026-08-13 2,584 --
Agent Context Carryover: more accurate voice agent transcription on LiveKit Martin Schweiger 2026-08-13 2,201 --
Best voice agent API in 2026: how to choose your STT foundation Kelsey Foster 2026-08-13 2,740 --
OpenAI Realtime API alternatives in 2026 (and how to migrate) Kelsey Foster 2026-08-13 2,629 --
The hard cases in speaker diarization: overlap, short turns, and noise Kelsey Foster 2026-08-13 2,579 --
Does Whisper do speaker diarization? Whisper + pyannote, and its limits Kelsey Foster 2026-08-13 2,546 --
From transcript to summary to follow-up items: Speech understanding gets an LLM upgrade -- 2026-08-12 1,635 --
AssemblyAI vs NVIDIA Parakeet and Canary: Choosing speech-to-text for production Kelsey Foster 2026-08-06 1,592 --
AssemblyAI vs Whisper Large-v3: Which speech-to-text should you ship? Kelsey Foster 2026-08-05 1,595 --
AssemblyAI vs Qwen3-ASR: picking speech-to-text for production Kelsey Foster 2026-08-05 1,428 --
AssemblyAI vs self-hosting on Baseten, Modal, or Fireworks Kelsey Foster 2026-08-05 1,637 --
How to build an AI scribe for therapy sessions that writes progress notes Kelsey Foster 2026-08-05 2,399 --
How to build real-time agent assist on streaming speech-to-text Kelsey Foster 2026-08-05 2,234 --
Which voice agent platform has the best developer experience? Kelsey Foster 2026-08-05 2,065 --
The real cost of self-hosting open-source speech-to-text Kelsey Foster 2026-08-05 2,479 --
Plushcap, by Matt Makai. 2021-2026.