AssemblyAI

Introducing Universal Streaming - an ultra-fast, ultra-accurate streaming speech-to-text model for voice agents 🚀 Universal-Streaming delivers ultra-low latency, superior accuracy, and intelligent endpointing at just $0.15/hr 👇

Want to extract transcripts from any YouTube video with code? 💻 This tutorial shows 3 ways to auto-transcribe YouTube videos with Python: - CLI download + transcribe - Python script approach - URL extraction (no download needed) Follow along here: assemblyai.com/blog/how-to-ge…

🗣️ Who said what? That’s the challenge speaker diarization solves—and it’s essential for making multi-speaker conversations useful in AI apps. Whether you're building meeting tools, call analytics, or transcription pipelines, getting accurate speaker separation is critical. In…

✨ Formatting updates for Spanish & German transcription users! Without proper punctuation, capitalization, and formatting, even accurate transcriptions feel awkward to native speakers. That's why we've just upgraded Universal with advanced text formatting specifically for…

⚡️ Want to build a voice agent that responds in under 500ms? In real-time voice applications, latency is everything. Even a one-second delay can break the conversational flow and degrade user experience. In our latest blog post, we break down how to build ultra-low-latency AI…

Another great entry for the @assemblyAI Voice Agents Challenge by Niko. Submissions open until July 27th - enter today!

🎯 Major speaker diarization improvements are now live! Our new in-house speaker embedding model just went live with 30% better accuracy in challenging audio environments: - Quiet interactions - Now captures barely audible segments that were missed before - Short responses -…

✅ Transcribe phone calls ✅ Identify speakers ✅ Detect sentiment ✅ Visualize data within call recordings Check out the full python tutorial from @thedataprof --> youtube.com/watch?v=71HvNA… #Python #DataScience #CallCenterAnalytics

The AssemblyAI Voice Agents Challenge is now live on @ThePracticalDev Build with our real-time speech-to-text API (300ms latency) and a chance to win $1,000. No credit card needed, $50 in free credits. Show us what you can build! Deadline: July 27 --> dev.to/devteam/join-t…

🚀 Ready to build the ultimate Voice Agent? Starting tomorrow, 7/16, join our challenge with @ThePracticalDev and build with our new Streaming Speech-to-Text model. $1,000 cash prize up for grabs. Stay in the loop: dev.to/challenges/ass…

🎙️ Want to convert voice to text in real-time in your JavaScript app? Check out our tutorial: “How to convert voice to text in real time using JavaScript” — a practical, step-by-step guide for developers looking to integrate speech recognition into web applications. Follow…

How do you turn messy, unstructured customer conversations into crystal-clear insights? Just ask the team at @hidovetail—a customer insights hub trusted by Amazon, Canva, Notion, Atlassian, and more. In our latest customer story, Dovetail shares how they’re using AssemblyAI to…

Human-in-the-loop reality in conversation intelligence 🧵 The challenge: Manual review is still needed for quality assurance, compliance monitoring, and catching AI hallucinations The cost: Scalability issues, inconsistency, privacy risks, and expensive overhead The solution…

Voice agent latency breakdown 🧵 STT: 90ms (Universal-Streaming) LLM: 200ms TTS: 75ms Network: 100ms+ Total: ~465ms end-to-end 🔑 Key insight: Disabling STT formatting saves precious milliseconds. Modern LLMs handle unformatted text perfectly, and every ms counts for…

🚀 Claude 4 models now available through our LeMUR API Transform your audio into actionable insights with our industry-leading speech-to-text API --- enhanced with Anthropic's most advanced AI models. Why LeMUR + Claude 4: 🎯 Unified Solution - Speech-to-text + advanced…

🩺 Build a voice-powered AI doctor that understands symptoms in real-time! Full Next.js tutorial with AssemblyAI, Clerk auth & Neon DB Perfect for healthcare SaaS developers 🚀 #NextJS #AIVoice #Healthcare #SaaS #WebDev youtube.com/watch?v=zjwj21…

Interesting to see all the voice agent projects people are building today 🤖 ✨ AI wellness companions 📞 Customer service automation 🎓 Real-time lecture note-taking ♿ Accessibility transcription tools 🔄 CRM call integrations The Universal-Streaming API is having its moment.…

Built a production-ready voice agent in 20 minutes using Pipecat 🔥 🎯 AssemblyAI for enterprise-grade STT 🎯 OpenAI for reasoning 🎯 Cartesia for natural TTS 🎯 Full Docker deployment Step-by-step tutorial 👇 bit.ly/4l8XIMh #VoiceAgent #BuildInPublic

Voice agent builders: you've optimized latency, but what about turn detection? ❌ Silence detection: "I want... uhh... a burger" → interruption ✅ Semantic endpointing: waits for sentence completion Universal Streaming: lightning-fast transcription + smart endpointing =…

Missed us at Zoom Developer Day? No problem! Check out our new Zoom RTMS resource center, featuring code samples and resources for building applications that integrate Zoom with AssemblyAI 👀 assemblyai.com/events/zoom-de…

🇪🇺 Exciting news for our European customers! Slam-1 and LeMUR are now available through our EU API endpoint, delivering complete data residency compliance without compromising on performance. What this means: ✅ Industry-leading speech recognition with EU data residency ✅…