AssemblyAI

We mispronounced every single item on the menu. Universal-3.5 Pro Realtime got all of them right anyway. 👇 Check out @martschweiger tutorial where he spun up a restaurant ordering agent on @livekit to put our latest model to the test. He ordered escargots à la bourguignonne, khachapuri adjaruli, kouign-amann, yuzu kombucha—the kind of proper nouns that usually wreck speech-to-text, and Universal-3.5-Pro Realtime transcribed each one perfectly. The reason it worked: agent context carryover. Most speech models transcribe each moment in isolation. Universal-3.5 Pro Realtime is the first to natively use the conversation's context—like the menu items your agent just listed—to sharpen what comes next. With Universal-3.5 Pro Realtime in LiveKit, turn on agent context carryover and the context flows into the model automatically.

Our team can't stop talking about the World Cup—so @martschweiger pointed our newest model, Universal-3.5 Pro, at a bilingual Cristiano Ronaldo interview to see how it handles the parts most models fumble. He switches between Portuguese and English mid-sentence. Universal-3.5 Pro transcribes both, natively. Then we pasted the YouTube description in as context, and it caught his Portuguese nickname "Cris," the interviewers' TV stations, and the club he was talking about. The same is true for the domains this model is built for: clinical documentation, contact center calls, and meeting recordings. See Universal-3.5 Pro in action👇

Universal-3.5 Pro Async is here — native code-switching across 18 languages, our best speaker diarization yet, and contextual prompting. All at $0.21/hr. Learn more: assemblyai.com/blog/universal…

Ordering a prescription by voice leaves no room for "close enough." Drug names, dosages, patient details—every word has to land. @stefanjblos built a voice agent that does exactly that—and gets the messy, high-stakes language of medicine.

Clicky by @FarzaTV is powered by @AssemblyAI Universal 3 Pro streaming model. I cloned it and upgraded it to Universal 3.5 to show how our newest realtime model can actively listen with context. The page itself becomes context for the speech model. As you scroll, Clicky updates Universal 3.5 with key terms from the screen so it can accurately recognize technical jargon, APIs, code, and other terms that speech models typically struggle to transcribe. Instead of guessing, the model already knows what to listen for.

C, Sí, or Sea?? The context carryover feature of Universal-3.5 Pro Realtime knows 🤓

➡️ Read the full launch blog: assemblyai.com/blog/universal… ➡️ Watch the demo: assemblyai.com/blog/universal…

Watch the video below for a full demo of how amazing our new Universal-3.5 Pro Realtime model is. Live, real demos always beat generic benchmarks! Available today in our API, Playground, and partner integrations.

Until today, a transcription model never knew what your voice agent just asked. The one we're launching today does. Universal-3.5 Pro Realtime from AssemblyAI is the first realtime speech-to-text model that takes your agent's side of the conversation as context. When your agent asks for an email and the caller rattles it off, the model already knows an email is coming, and captures it perfectly. Same for an order number read fast, an account ID, a medication, or a name spelled out over poor quality phone line.

@MasteraSnackin @metaview nice!! Thanks for building with us @MasteraSnackin! 🚀🎙️

Tonight at @Metaview’s London office, I built a voice agent in under an hour using @AssemblyAI’s Voice Agent API 🎙️ It’s a voice-powered Choose Your Own Adventure game: the agent narrates, gives 3 choices, and users reply by voice or tap. Stack: AssemblyAI + Gemini + AIStudio

@mark_oyk nice!! thanks for building with us! 🚀

I just completed my AssemblyAI hackathon project

@pattiatx @metaview thanks for building with us @pattiatx!! 🎙️💙

Tonight at @Metaview's London office I built a voice agent in under an hour with @AssemblyAI's Voice Agent API ⚡ What I built: the Berghain Bouncer 🎙️ — it interrogates you in German, cuts you off, then stamps NEIN on screen.Built in 60 minutes. Maintains stricter standards than its creator 💀 Tech stack: Claude + vanilla JS github.com/PKusch/berghai… #AAIVoiceAgentAPI

You can call a phone number and ask an AI to find you the perfect vinyl based on a mood or memory. We're kicking off our weekly Voice Agent Spotlight with The Record Store Oracle, built by @Gyurmatag, and honestly, the personality in this one sets the bar. Speak a feeling. An era. A specific road trip. The agent listens, thinks, and recommends a record. Under the hood it's a surprisingly clean stack: → @AssemblyAI Voice Agent API (STT + LLM + TTS in one) → @Twilio Media Streams for real phone call handling → @Cloudflare Workers + Durable Objects for hosting → Single WebSocket, no transcoding overhead The UI contains a live orb that pulses as the agent thinks, with a real-time transcript of tool calls happening beneath the surface. New project every Wednesday. More builders, more stacks, more ideas for what voice AI can actually do. 🎙️Demo The Record Store Oracle: voice-agent.cfi-ops.workers.dev 🏆Full showcase: assemblyai.com/showcase

AI medical voice agent in production. - 14 hours of call volume - 38 appointments booked, more captured revenue for practices - 11 appointments cancelled -> reduces no show rate and saves cost on valuable chair time Thx @livekit @cartesia @rimelabs @AssemblyAI

This Wednesday afternoon you could have a working voice agent you built yourself. @dan_aai from @AssemblyAI is running a live workshop. Claude Code + AssemblyAI Voice Agent API, built from scratch in about an hour. 🤖 Claude Code does the building. You direct it. No coding experience required. Starter code to fork. Q&A the whole way through. free. Jun 10. 10AM PT. → assemblyai.zoom.us/webinar/regist…