Loading video...

Video Failed to Load

Go Home

Introducing our unified Voice Agent API! ⚡️ Quickly and easily build voice agents that listen, think, and respond in real-time, as naturally as a human can. Powered by the industry's fastest, most performant speech recognition and voice synthesis models to deliver: -Natural-sounding real-time conversations -Revolutionary interruption handling -Choice of...

726,214 views • 1 year ago •via X (Twitter)

10 Comments

Deepgram's profile picture
Deepgram1 year ago

Our Voice Agent API was designed to tackle the toughest development challenges with ease: -Noisy environments -Network and model latency -Complex conversations -Context -Action taking -Controllability Developers can now quickly and easily build voice agents for customer support, order taking, and more with just an API call.

Deepgram's profile picture
Deepgram1 year ago

In this next demo, our AI voice agent uses next-gen end-of-speech prediction to handle long pauses while capturing phone number IDs. The result? Responsive, natural conversations with company and product-specific context for top-notch customer support.

Deepgram's profile picture
Deepgram1 year ago

We’re also excited to share an early proof-of-concept prototype using our new voice agent API. Try it out firsthand with this interactive demo:

Deepgram's profile picture
Deepgram1 year ago

At Deepgram, we've spent nearly a decade building and deploying thousands of voice AI models, processing billions of hours of conversational audio. 🚀 We've applied these insights into our new Voice Agent API, optimizing for exceptional performance that redefines human-machine interaction. Experience the difference for yourself. Learn how you can get access.

Hillcrest Card Company 🏳️‍🌈🍉🏳️‍⚧️🚲🇨🇺's profile picture
Hillcrest Card Company 🏳️‍🌈🍉🏳️‍⚧️🚲🇨🇺1 year ago

When you claim that your bot can perform as naturally as a human can, that's how you tell us that you are dishonest and are willing to lie to consumers for profit.

MargauxR's profile picture
MargauxR1 year ago

AI Sucks. No offense.

Rami M's profile picture
Rami M1 year ago

Cool! Can we use third party TTS? also on a different note, can you please add Arabic language support your nova STT model?

Kelly4Infowars's profile picture
Kelly4Infowars1 year ago

AI can never be smarter than a human on multiple levels......it's only level is academic-- it has no soul--- and it's only as smart as the jack ass who enters it all. think like a leftist you got a leftist geared robot wait until it's your judge sand juries and has no emotions to weigh out differen scenarios that are more humanitarian

Yipei WEI's profile picture
Yipei WEI1 year ago

That Voice Agent API sounds amazing for real-time conversations! Have you checked out @TenFramework? They have some cool tools too. Would love to see how their TEN-Agent could integrate with your tech!

burner account 8888's profile picture
burner account 88881 year ago

FUCK YOU AND YOU AI that we are now re-opening coal plants to run. AI is not worth the energy needed to run it. So FUCK AI

Related Videos

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:

Andrew Ng

87,484 views • 1 year ago