AssemblyAI - Videos
Back to Channel
What Actually Defines Success for Voice AI Agents? π€
The CEO of Aviary AI breaks down what really matters when deploying voice agents. π‘ Spoiler: it's not perfectionβit's task completion. Are you building voice AI? How do YOU measure success? π β¬β¬β¬β¬...
What Actually Defines Success for Voice AI Agents? π€
The CEO of Aviary AI breaks down what really matters when deploying voice agents in financial services. π‘ Spoiler: it's not perfection β it's task completion. Are you building voice AI? How do YOU ...
Meet the Voices Shaping the Future of Voice AI ποΈ
From fintech voice agents to real-time AI infrastructure β meet the panelists pushing the boundaries of what voice AI can do. π Aviary AI, Trellis (YC W'22), and AssemblyAI are all in the building....
The Secret to Eliminating Latency in Voice AI π§
The co-founder of Trellis (YC W'22) shares a game-changing approach to cutting voice AI latency β script it out, cache it ahead of time, and stop scrambling at the last second. β‘ Are you using pre-...
Voice AI Is Taking Over β Whether You're Ready or Not π
From engineers coding by voice to Alexa ads with Pete Davidson β the consumer shift to voice is already happening. ποΈ The CEO of Aviary AI explains why traditional mobile banking apps are on their ...
Do Different AI Voices Actually Drive Better Results? πποΈ
Female voices are outperforming male voices in voice AI calls β longer conversations, better responses, better results. π€― The CEO of Aviary AI breaks down their A/B testing findings and why persona...
How to Handle Interruptions in Voice AI Calls π€«ποΈ
Building voice agents? Here's the real talk on interruptions β sometimes you wait longer, sometimes you just shut up and let them talk. π The panel breaks down why chasing perfection is the wrong g...
Why This Voice AI Company Hasn't Touched Inbound Calls Yet π
Before jumping into inbound, Aviary AI is doing something most voice AI companies skip β auditing the knowledge base first. π§ If the docs are outdated or irrelevant, your inbound agent will fail no...
Why AssemblyAI Says No to Cool Tech to Build Better Voice AI π«β¨
Sometimes the coolest solution isn't the right one. AssemblyAI's Head of Real-Time breaks down why they skip the flashy tech and go back to first principles β even using methods from 2015 β to make...
From 7-Second Lag to Sub-1.6s β The Voice AI Latency Journey β‘ποΈ
7 seconds. Then 3.5 seconds. Now sub-1.6 seconds β and clients STILL notice every millisecond. β±οΈ The CEO of Aviary AI breaks down the two things enterprise customers actually care about in voice A...
The One Metric That Proves Your Voice AI Calls Are Actually Working β ποΈ
Did the call end with a natural goodbye? That's the metric Aviary AI uses to prove their voice agents are performing β and clients love it. π Forget obsessing over how it sounds. The real question ...
Universal-3 Pro Streaming Speaker Labels demo
Speaker diarization in real-time streaming just hit a new bar. Try it live in the no-code playground: https://www.assemblyai.com/playground?utm_source=youtube&utm_medium=referral&utm_campaign=shor...
Universal-3 Pro: Office Icebreakers
We tested Universal-3 Pro Streaming in our office with some icebreaker questions. Try Universal-3 Pro Streaming live in our demo! https://www.assemblyai.com/universal-3-pro-streaming?utm_source=y...
Building Quso.ai: Autonomous social media, the death of traditional SaaS, and founder lessons
Vedant, co-founder of Quso.ai, shares the journey from a simple long-video-to-shorts tool to a full autonomous social media engine β plus why speech-to-text quality was non-negotiable from day one....
Prompt Engineering Workshop: Universal-3 Pro
AssemblyAI Applied AI Engineers hosted a live jam session where they walked through how prompting works in Universal-3 Pro. Get the TL;DR on: - How prompting transcription works - Live examples a...
Code Switching in Real-Time | Universal-Streaming Speech-to-Text
Code-switching is how multilingual speakers actually talk and voice-to-text has never kept up. Until now. In this video, Santiago test's AssemblyAI's Universal-Streaming model, which transcribes s...
The Real State of Voice Agents: Lessons from Founders Who've Deployed Millions of Calls
At our New York office, we hosted a live panel on what it really takes to build voice agents in production. Joined by Blesson from Aviary AI (outbound voice for financial services), Craig from Tre...
Building Needle: Vibe automation, RAG workflows, and founder lessons
Jan Heimes from Needle shares what it's really like building a vibe automation platform with built-in RAG, plus honest founder insights on burnout, validation, and choosing the right co-founder. β¬...
Universal-3 Pro transcribes ASMR
Original video used to get audio: https://www.youtube.com/watch?v=jE6x0TXsYUc Try Universal-3 Pro in our playground with your own audio files: https://assemblyai.com/playground?utm_source=youtube&...
Beware the Dogma: Building Earmark
Mark from Earmark shares his advice for founders. Watch the full episode here: https://youtu.be/Fians2EMCeY Try Earmark here: https://www.tryearmark.com/ β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ We...
Privacy by design: Building Earmark
Sanden from Earmark shares two critical lessons for building voice AI products. Watch the full episode here: https://youtu.be/Fians2EMCeY β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://ww...
Building Earmark: Real-time voice AI, privacy by design, and founder lessons
Mark Barbir and Sanden Gocka, founders of Earmark, share what it's really like building a real-time voice AI product for product managers. We cover: - The origin story of Earmark - Dogfooding thei...
Universal-3 Pro Technical Overview
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
55% of Users Abandon Voice Agents (Here's Why)
Watch to see what 455 builders told us about why users abandon voice agents. Read the full report here: https://assembly.ai/var β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assembly...
How Calabrio boosted customer satisfaction by 80% and accelerated global expansion with AssemblyAI
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
Building Ambient AI Medical Scribes: Best Practices
π Best practices for building ambient AI scribes: https://www.assemblyai.com/docs/medical-scribe-best-practices?utm_source=youtube&utm_medium=referral&utm_campaign=tutorials&utm_content=mart_ambien...
Metaview Customer Story | AssemblyAI
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c/...
Best Free Speech-to-Text APIs in 2025 (Compared)
Looking to add voice transcription to your app without breaking the bank? In this video, we compare the best free speech-to-text APIs and open source alternatives available to developers in 2025. ...
Real-time Speech-to-Text APIs for Voice Agents: Beyond WER to Real-World Performance
In this comprehensive guide, we reveal the evaluation criteria that separate natural-feeling voice agents from frustrating robotic experiences. Learn why sub-500ms latency isn't optional, how seman...
November 2025 Recap
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
4 Expert Tips for Building an Accurate AI Meeting Notetaker
In this video, we share four essential tips for developers building an AI meeting notetaker. Whether you're working on a productivity app, an AI assistant, or a meeting transcription tool, these te...
What is Conversation Intelligence? AI Speech Analysis for Sales, Support & Product Teams
Discover how Conversation Intelligence is transforming the way businesses capture and analyze customer interactions. Most organizations capture less than 30% of valuable conversation data, missing ...
Introducing Universal-Streaming
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
Dovetail Customer Story | AssemblyAI
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
Conversation Intelligence starts with AssemblyAI
VEED Customer Story | AssemblyAI
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
September Release Recap | AssemblyAI
Big September Updates from AssemblyAI! This month we shipped five major updates that make speech recognition more global, accurate, and easier to use than ever: βΈ In-app playground β test Async ...
aai fern docs demo 2
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
Supernormal Customer Story | AssemblyAI
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
Echo AI Customer Story | AssemblyAI
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
Siro Customer Story | AssemblyAI
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ CONNECT β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬ π₯οΈ Website: https://www.assemblyai.com π¦ Twitter: https://twitter.com/AssemblyAI π¦Ύ Discord: https://discord.gg/Cd8MyVJAXd βΆοΈ Subscribe: https://www.youtube.com/c...
Everything AssemblyAI Released in October β 90 Second Update
From Universal Multilingual Streaming to LLM Gateway, we've been busy making speech AI faster, safer, and easier to build with. In this video, I cover: - Universal Multilingual Streaming β Real-ti...
Best Practices for Building High-Performance Voice Agents with AssemblyAI
Building voice agents often feels like choosing between speed and accuracyβbut it doesn't have to be that way. In this tutorial, I demonstrate four essential best practices for building high-perfor...
How to Switch from LeMUR to AssemblyAI's LLM Gateway
This video provides a straightforward migration guide for developers transitioning from LeMUR to AssemblyAI's LLM Gateway. Learn how to access multiple LLM providers (Google Gemini, OpenAI GPT, and...
AssemblyAI's New Feature: Automatic Speaker Identification for Production Apps
Turning raw transcripts into production-ready output shouldn't require complex post-processing pipelines. In this video, Mart from AssemblyAI demonstrates how our new Speaker Identification feature...
How to Build a Real Time Agent Assist Voice Agent for Call Centers
In this video, we break down how Real Time Agent Assist works and show you how to build your own system. We explore the key components: real-time transcription with AssemblyAI, AI-powered analysis ...
How to Evaluate APIs for Speaker Diarization
Build smarter call center tools, podcasts, and meeting apps with AssemblyAIβs Speaker Diarization API. π Try diarization for free with AssemblyAI: https://www.assemblyai.com/?utm_source=youtube&ut...
Build an AI Assistant for Meeting Scheduling Step by Step!
π Get your AssemblyAI API key here: https://www.assemblyai.com/?utm_source=youtube&utm_medium=referral&utm_campaign=yt_jason_2 π Github repo: https://github.com/AssemblyAI-Community/simple-livekit...
How to Build and Deploy an AI Voice Agent using Pipecat
π Get your AssemblyAI API key here: https://www.assemblyai.com/?utm_source=youtube&utm_medium=referral&utm_campaign=yt_jason_1 Github repo: https://github.com/AssemblyAI-Community/pipecat-cloud-ex...
Model Context Protocol (MCP) explained (with code examples)
π Get an AssemblyAI API Key: https://www.assemblyai.com/dashboard/signup?utm_source=youtube&utm_medium=referral&utm_campaign=yt_ry_694 π§βπ» GitHub repo: https://github.com/AssemblyAI-Community/mcp-p...