Pinned Tweet
๐๐ป๐๐ฟ๐ผ๐ฑ๐๐ฐ๐ถ๐ป๐ด ๐๐ด๐ผ๐ฟ๐ฎ ๐๐ด๐ฒ๐ป๐๐ ๐ฆ๐๐.
Building a voice agent is easy in a demo.
Production is where the plumbing shows up: auth, RTC channels, STT/LLM/TTS config, session lifecycle, recovery.
Agora Agents SDK helps developers handle that layer faster.
agora.io/en/blog/agora-agentโฆ
#AIAgents #VoiceAI
Voice AI for Bharat: The Diwali Edition ๐ช xitter.cf/i/broadcasts/1qKVmyYbLโฆ
Watch the full episode ๐ podcast.convoai.world/episodโฆ
Does classifying a customer request need the same model as holding a conversation?
In this episode of the Convo AI World Podcast, @hermes_f speaks with @neal_k_patel, co-founder of @scaledown_team, about choosing models for the specific jobs inside an AI application.
๐๏ธ Beyond Voice Chatbots: Build AI Agents That Take Action xitter.cf/i/broadcasts/1kKzDPXyeโฆ
๐ฃ๏ธ User: "STOP!"
๐ค AI Agent: "Sure! But first, let me explain..."
Why is interrupting a Voice AI agent so hard? ๐
Because stopping audio playback โ cancelling the entire pipeline.
VAD โ ASR โ LLM โ TTS โ Playback
Barge-in is a real-time coordination problem, not just a mute button.
That's where Agora Conversational AI comes in. โก
#VoiceAI #Agora #AIEngineering
Inside Agora Conversational AI: What Powers a Real-Time AI Agent? xitter.cf/i/broadcasts/1PKqrNLyzโฆ
Building a conversational AI device means getting speech recognition, the LLM, voice generation, memory, and connectivity to work together in real time.
Our SVP of Product, Patrick Ferriter, joined @iotforall to discuss why teams want help integrating those components while retaining the flexibility to choose their models and voices.
๐๏ธ Will conversational AI take over our devices? Patrick Ferriter from @AgoraIO joins the IoT For All #podcast to discuss building real-time #AI voice experiences, even on bad networks. โก๏ธ youtu.be/qEBnlgaEUBY
Take a closer look at these projects in Agora Dev Digest๐
medium.com/agora-io/agora-deโฆ
Some cool things developers have been building with Agora lately ๐
โ๏ธ Spidey is a friendly AI companion that helps you manage tasks by voice. By @HaimantikaM .
โ๏ธ Voice Arena brings two voice agents with different turn-taking and interruption settings into a live battle. By @HarishKotra .
๐๏ธ Jev VAD explores when a voice agent should listen or keep talking. By @SoCalJayF .
๐ง An interactive podcast where you can jump in and talk to two AI hosts. By @zicojzc.
Excited to welcome @soniox_ai to Agora Conversational AI platform! More ways for developers to build responsive, multilingual voice experiences ๐ค
Weโre excited to announce that @AgoraIO has selected Soniox as a speech-to-text provider for its real-time Conversational AI platform.
For over a decade, Agora has built the global network infrastructure that connects people through real-time voice, video, and messaging. Today, that same carrier-grade infrastructure is powering a new era of interactions: humans talking directly with AI.
For voice AI, moving audio in real time is only part of the problem. The system must understand natural, conversational speech instantlyโaccurately capturing critical details despite accents and noisy environments.
Soniox brings:
โข Native-speaker accuracy across 60+ languages
โข Ultra-low latency for real-time conversations
โข Seamless multilingual speech and mid-sentence language switching
โข High precision on names, numbers, IDs, and other critical details
โข Reliable performance on real-world audio at production scale
Agora provides the orchestration for Conversational AI and the infrastructure for real-time communications. Soniox provides the intelligence for understanding spoken language.
Together, weโre making it easier for developers to build voice AI that can communicate naturally with people around the world.
Excited to partner with the Agora team and help power the next generation of conversational AI.
Getting Started with Agora Conversational AI xitter.cf/i/broadcasts/1pKdRDvrbโฆ
Agora retweeted
If you're curious to see real applications of AI voice tech in action๐
Moderating a killer panel happening in London next week for Deep Tech Week!!!! Would love to see you there ๐
Space is limited & sharing more deets below: luma.com/cjumnkfs
๐๏ธ Announcing the Agora Conversational AI LinkedIn Live series, starting this October.
Grab your seat: linkedin.com/events/75104485โฆ
๐๐ถ๐ฟ๐๐ ๐๐ฒ๐๐๐ถ๐ผ๐ป: ๐๐ฒ๐๐๐ถ๐ป๐ด ๐ฆ๐๐ฎ๐ฟ๐๐ฒ๐ฑ ๐๐ถ๐๐ต ๐๐ด๐ผ๐ฟ๐ฎ ๐๐ผ๐ป๐๐ฒ๐ฟ๐๐ฎ๐๐ถ๐ผ๐ป๐ฎ๐น ๐๐
We'll go from "What exactly does Agora do in a Voice AI stack?" to getting something up and running.
๐
October 1
โฑ๏ธ 30โ40 mins
๐ LinkedIn Live
No slides-only webinar. We'll actually open the tools and build.
Giving people time to finish their thoughts ๐ฌ
@SoCalJayF connected @typesafeai Jev to Agora ConvoAI to explore how live transcripts and conversation context can help voice AI recognize when someone has finished speaking. Take a look at his demo ๐
One really cool use case Iโve been exploring with Jev: a semantic VAD for real-time voice AI.
I plugged it into @AgoraIO ConvoAI and used the live transcript + recent conversation as context to decide whether the user has actually finished speaking.
That makes Jev surprisingly good at handling things like hesitation, unfinished thoughts, and those moments where you stop talking for a second because youโre still figuring out what you want to say.
Itโs a nice example of where Jev fits really well in a real-time AI loop.
Hereโs what it looks like in action ๐
A live podcast platform with AI hosts โ built by @zicojzc using Gemini 3.8 Flash TTS, Gemini 3.5 Transcribe Live, and Agora RTC!
It feels less like listening to an episode and more like stepping into the conversation:
๐๏ธ Everyone in the room hears the same show, and listeners can jump in and talk to the hosts
๐ซธ The joiner interrupts, and the AI hosts acknowledge the interruption immediately
๐ฃ๏ธ Gemini 3.8 Flash TTS streams a two-host answer, and then the podcast picks up where it left off
We're stepping into a new era of real-time AI communication. What do you think @googledevs @GoogleDeepMind?