AssemblyAI @AssemblyAI

Access powerful AI models to transcribe and understand speech via a simple API. Try our no-code playground for free 👉 https://t.co/YPCK9mqDG6 assemblyai.com Joined October 2017

Tweets

3K
Followers

46K
Following

414
Likes

4K

Harnoor Singh @iHarnoorSingh

3 weeks ago

Honor to host NYC Voice AI Meetup this week for @AssemblyAI 100+ people showed up. Great collaborating with @livekit and @boardyai Building with voice is so much fun right now, comment down what you're building with voice, TTS, or voice agents :)

2 1 37 12K 2

View Details

AssemblyAI @AssemblyAI

2 days ago

SF, check your mailboxes 👀 Invites to our SF Tech Week Voice Agent workshop went out this week. Not sure "vintage" feels quite right, but we can't wait to see what you code into your voice-agent sidekick to clip onto your backpack and relive your childhood dreams. Didn't get one? Request an invite 👇 luma.com/w9e4qgol

4 3 9 4K 0

View Details

Datweb3guy @Datweb3guy

7 days ago

Most intake systems optimize for collecting fields, but guess what? > HangON optimizes for preserving intent A voice first front desk for operations teams, service desks, and community programs, built for the moments a misunderstood first handoff creates hours of rework Fully built with @AssemblyAI's Voice Agent API People rarely explain real requests in neat form fields HangON lets callers explain naturally, then asks only the questions the workspace has configured The result is a structured request, without forcing people through a rigid maze Before anything is prepared, HangON reads the request back The caller can correct it, clarify it, or confirm it. That small interaction matters, because "I understood you" is not the same as "I am allowed to act." The architecture runs from a browser microphone, through AudioWorklet capture, into a server minted AssemblyAI session, through workspace owned prompts and tools, to a signed confirmation, an idempotent request store, and an optional signed webhook Confirmation is not just a boolean, because HangON signs approval against the exact workspace, summary, details, route, and idempotency key Change one detail and the approval no longer matches We built this with just one goal: make voice intake feel human without making systems less accountable HangON is for teams that need better first handoffs, not more forms For callers, it feels conversational For operators, it produces a request they can inspect and trust Try the public demo: tryhangon.vercel.app Thank you

6 1 12 1K 1

View Details

AssemblyAI @AssemblyAI

2 days ago

BTW, we intentionally spelled Minoxidil as “Minoxidril”; the model spells it exactly as provided in the keyterms.

0 0 2 216 0

View Details

AssemblyAI @AssemblyAI

2 days ago

Blurt: push‑to‑talk dictation on the AssemblyAI Dictation API The Dictation API converts a spoken clip into finished text. Filler words and false starts are removed, and the output can be formatted as notes, a commit message, or a reply to a customer. Built on Universal‑3.5 Pro, it supports 19 languages, processes short clips in under a second, and costs $0.62/hr. Link in comments below

6 0 11 1K 1

View Details

AssemblyAI @AssemblyAI

2 days ago

@johncrickett We're so glad :)

0 0 1 77 0

View Details

AssemblyAI @AssemblyAI

2 days ago

@LubaYudasina Excited!

1 0 1 30 0

View Details

AssemblyAI @AssemblyAI

2 days ago

@itsjdraven Thank you for sharing!

1 0 1 18 0

View Details

AssemblyAI @AssemblyAI

2 days ago

@shelleymaeph thank you for sharing!!

0 0 0 8 0

View Details

Milan Jovanović @mjovanovictech

a week ago

I spent the morning building a small video transcription platform for myself. Took a few back-and-forths with Astra to get this built and deployed on my Dokploy instance. Part of my work to replace existing SaaS subscriptions with my own tools. This saves ~120/year.

7 2 30 6K 4

View Details

AssemblyAI @AssemblyAI

2 days ago

@mjovanovictech thank you for all the love :)

1 0 1 17 0

View Details

AssemblyAI @AssemblyAI

2 days ago

assemblyai.com/blurt

0 0 0 229 0

View Details

Harnoor Singh @iHarnoorSingh

a week ago

if you don't have anything to do this weekend, We have something for you! We’re kicking off Voice Hackathon Week: Hack into Dictation with @AssemblyAI Join one of the most talented builder communities across the globe luma.com/qwckwa01

0 1 17 3K 3

View Details

luba yudasina @LubaYudasina

a week ago

Dylan from @AssemblyAI started building in the voice infra space 5 years before it became obvious. Loved visiting the office and hearing his story - coming soon!

2 2 37 2K 4

View Details

Kartik @Kartikio

4 days ago

@maxktz @raycast I found blurt today, open source, built by @AssemblyAI to showcase its dictation api, its fast and very accurate, you can just build your own with dictation api and you get $100 credits on assembly as a new user, crazy value assemblyai.com/blurt

0 1 0 230 0

View Details

Harnoor Singh @iHarnoorSingh

3 days ago

Voice is becoming the default way we communicate across all apps. Let’s integrate dictation into your apps, such as lengthy forms (Google Form / Typeform), job applications, paperwork, and more. Meet the fastest way to ship voice input @AssemblyAI Dictation API: x.com/AssemblyAI/sta…

2 1 18 11K 4

View Details

AssemblyAI @AssemblyAI

2 days ago

@Marisdigitals11 👏👏

1 0 1 20 0

View Details

Stellamaris ❤️| π (privacy szn) @Marisdigitals11

5 days ago

Built CareEcho for the @AssemblyAI Voice Hackathon CareEcho is a multilingual, voice-first health memory that helps patients remember what happens before, during, and after doctor visits. ▪️Speak your symptoms --> build a health timeline ▪️Record a consultation → ask later: “What did my doctor say about my medication?” CareEcho answers from the actual visit evidence, not guesses. Built for accessibility, multilingual users, older adults, and anyone who struggles to keep track of health information. Your health memory, in your voice. 💙

8 8 22 602 0

View Details

AssemblyAI @AssemblyAI

2 days ago

Fingers can't type as fast as your brain moves? That's why the little mic icon is showing up everywhere: notes apps, email, CRMs, coding tools, patient charts. People talk, the app writes it down. On Sept 24 @iHarnoorSingh is showing SF how to build that feature with our Dictation API. Save your seat → luma.com/xwnkujzr?utm_s…

3 2 9 12K 1

View Details

AssemblyAI @AssemblyAI

3 days ago

Dear developers, Forms are broken. Questions across multiple pages and endless fields. A slow, painful experience. What if we could answer everything… with a single voice prompt? With dictation, users can input text up to 3× faster. That's why, we’ve launched our Dictation API: assemblyai.com/dashboard/play…