Behind every great app is a great API. We power the real-time APIs for live voice, video, and chat in the world's biggest apps. (NASDAQ: $API)
Santa Clara, CA
- Tweets 5,192
- Following 1,271
- Followers 26,576
- Likes 3,858
𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗔𝗴𝗼𝗿𝗮 𝗔𝗴𝗲𝗻𝘁𝘀 𝗦𝗗𝗞.
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-agent…
#AIAgents #VoiceAI
5
6
24
8,335
A live podcast platform with AI hosts – 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:
🎙️ Everyone in the room hears the same show, and listeners can jump in and talk to the hosts
🫸 The joiner interrupts, and the AI hosts acknowledge the interruption immediately
🗣️ 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?
3
13
849
Tone and delivery shape how spoken communication is understood, and Google’s latest Gemini 3.8 Flash TTS and Flash-Lite TTS models address a persistent limitation in voice AI by giving developers finer control over how generated speech sounds and adapts throughout a conversation.
We’re excited about the new models’ ability to direct emotion, pace, character, and accent – plus a library of 20,000+ voices!
Our thoughts on what this opens up for real-time voice builders: agora.io/en/blog/a-new-gener…
Create and deploy custom audio with our new text-to-speech models:
🔵 Gemini 3.8 Flash TTS: Design unique voices with distinct accents and characteristics.
🔵 Gemini 3.8 Flash-Lite TTS: Built for efficiency and scale, choose from your created styles or our expansive production-ready library.
4
4
10
1,291
Your AI agent gets an empty response from a tool—then makes up the data it needs to keep going. What catches it?
In the latest episode of Convo AI World podcast, host @hermes_f speaks with Dustin Allen from Trinitite about governing AI agents in production.
Watch the episode 👉 podcast.convoai.world/episod…
1
6
673
Building voice AI with Gemini?
Join us live on Discord with @thorwebdev from @GoogleDeepMind and @hermes_f from Agora.
We’ll cover the latest real-time capabilities, natural turn-taking, interruptions, tool use, evals, and what it takes to ship dependable voice agents.
📅 Thursday, Sep 17 at 9 AM PT / 12 PM ET
Link: bit.ly/4xAzPDQ
2
10
32
6,088
When it comes to voice-agent workloads, one size doesn’t fit all–and that’s what Google Gemini’s 3.8 Live update addresses.
⚡️ 3.8 Live for fast, direct interactions such as FAQs, routing, order status, and scheduling.
🧠 3.8 Live Extended Thinking for investigation, planning, and workflows spanning multiple tools.
We looked at where each model fits in production voice AI: agora.io/en/blog/gemini-3-8-…
🗣️ Introducing Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking.
These advanced audio models are built for natural conversation, featuring major upgrades in turn-taking and near real-time reasoning. They also significantly streamline how you build intelligent voice agents.
Until now, advanced reasoning and reliability came at the cost of high latency and the complexity of cascaded, multi-model pipelines. Stitching together separate speech-to-text, reasoning, and text-to-speech models adds delay and inflates costs.
By replacing that stack with a single multimodal API call, these two models make building highly responsive voice agents simpler and cost-effective.
🧵 Here’s what you can build with them:
1
1
8
6,723
Just gave GPT‑Live‑1 a seat in our meeting today. It felt so natural!
It listened to our team’s discussion, summarized it, and added a task to the Kanban board.
First time actually having a meeting with an AI. Pretty fun.
Powered by @AgoraIO RTC, Conversational AI and @OpenAI GPT‑Live‑1 API
3
6
26
25,358
We’re excited to see this model’s full-duplex capabilities move the industry closer to human-to-AI conversations that flow more like human-to-human ones – much like our mission to make real-time video, voice and conversational AI ubiquitous.
Our take: agora.io/en/blog/voice-ai-th…
GPT-Live-1 is now available in the API.
Bring ChatGPT’s natural back-and-forth to your app, with voice agents that listen while they speak and work with the models and harness you choose.
2
4
7
798
AI Toys Come Alive! Real-Time Voice AI × Interactive Entertainment
What happens when toys can talk, listen, remember, and respond naturally in real time?
@AgoraIO, in collaboration with @awscloud, is bringing AI builders, robotics companies, voice AI innovators, and interactive entertainment creators together in Tokyo to explore what’s next for AI toys, AI companions, virtual characters, conversational AI, and connected devices.
Featuring @kotoba_tech, INBREEZE, AnotherBall, @yukaikk, and @MiniMax_AI, plus live demos and networking.
📷 September 17 | 17:00–21:00
If you’re building the future of AI, robotics, gaming, toys, voice AI, or interactive entertainment, we’d love to have you join us!
Register: luma.com/nts51f1c
1
2
501
AI makes a guess, then has to generate a video to prove it 😄
Built with Agora RTC, Interactive Whiteboard, and @reactorworld FastH3. Definitely more fun with friends!
Made a realtime Draw & Guess game with FastH3.
AI joins as a player, it sees the sketch, makes a guess, then uses FastH3 to generate a matching video as proof. AI only wins if both the guess and the video are right. Played it with my friends, it got pretty funny.
Built with @AgoraIO RTC + Interactive Whiteboard and @reactorworld’s FastH3.
I’ll publish the demo and open-source it soon
1
7
776
Want to use Gemini 3.5 Transcribe Live in a voice agent without committing the rest of your stack to a single provider?
Agora’s new TypeScript integration lets you add Gemini as the speech-to-text layer while retaining control over the LLM and voice.
Using 𝘎𝘦𝘮𝘪𝘯𝘪𝘛𝘳𝘢𝘯𝘴𝘤𝘳𝘪𝘣𝘦𝘚𝘛𝘛 in the Agora Agents SDK, developers can:
🔌 Pair Gemini transcription with an OpenAI-compatible LLM and providers
🌍 Handle multilingual or code-switching conversations
📚 Add custom vocabulary and other domain-specific language
📡 Use Agora RTC for live audio while RTM delivers transcripts, agent state, metrics, and errors to the application
🔐 Keep the Google API key and Agora App Certificate safely on the server
Start building with Gemini 3.5 Transcribe Live and Agora Conversational AI 👉 agora.io/en/blog/using-gemin…
4
2
10
12,868
@AgoraIO Joins @tib_tokyo as a Partner
We're excited to announce that Agora has joined Tokyo Innovation Base (TIB) as a TIB Partner.
Operated by the Tokyo Metropolitan Government, TIB brings together startups, entrepreneurs, corporations, investors, and ecosystem partners to accelerate innovation across Japan.
Through this partnership, we're excited to contribute our expertise in real-time engagement infrastructure, Voice AI, and Conversational IoT—helping developers build immersive live experiences and natural conversational interactions.
As we continue expanding in Japan, we look forward to collaborating with startups and innovators to shape the future of real-time experiences and conversational AI.
#Agora #TokyoInnovationBase #VoiceAI #Japan
2
1
5
726
ConvoAI World Podcast: Dustin Allen, Co-founder @ Trinitite nitter.net/i/broadcasts/1mxPaZZNy…
1
4
1,479
Agora retweeted
Day 2 of #VoiceForBharat
Today BetterSaid got personality, a job, and limits.
It’s an @AgoraIO -powered Android voice agent for spoken-English practice.
Agora handles the real-time layer:
RTC voice channel
RTM transcripts/events
agent session flow
interruption handling
voice playback
Added:
- patient English coach persona
- Hindi/Hinglish support via Sarvam ASR
- @MurfAIStudio Falcon TTS
- guardrails: no shaming, diagnosis, exam/job guarantees, medical advice, or credential handling
Learning: voice agents are not just prompt + TTS. If ASR drops code-mixed speech, the LLM never sees the real intent.
#VoiceAI #AIAgents #AndroidDev #Agora #MurfAI
2
6
668
Voice AI just took full control of a 3D anatomy app.
No mouse. No buttons. Just talk. It focuses on the exact body structure + explains it in real time.
I integrated @AgoraIO Conversational AI into this @threejs anatomy app. The voice agent controls the 3D UI, focuses on the right structures, and explains them in real time.
Original 3D app by @thebuggeddev.
3
6
35
152,387
Build a Voice AI agent from a prompt—then test it on a real call minutes later!
Agora’s new Console features Concierge, an AI assistant that recommends a template and ASR, LLM + TTS stack based on your use-case, applies changes only after approval, and takes you from draft to deployment.
Learn more 👉 agora.io/en/blog/introducing…
2
3
13
1,416
@OpenAI didn’t publish GPT-Live's end-to-end latency. So Agora Media Lab measured it on an iPhone – with repeatable speech, dual-track waveform recordings, and controlled network impairment.
agora.io/en/blog/openai-didn…
#RealTimeAI #VoiceAI
5
2
14
5,626
Agora CLI was created to solve this major developer bottleneck - and we're glad to see devs loving this new release :) Also, a football tactics coach use case is so timely given the world cup fever engulfing us!
Voice agents are getting scary easy to build.
I used Agora’s CLI to build a football tactics coach that explains formations, pressing, and match situations out loud.
I can even interrupt it in middle conversation.
demo + setup below:
4
10
2,306