Real-time Voice AI Agents
We are open-sourcing the easiest way for developers to build real-time Voice Agents and Virtual Avatars into any app—telephony, web, mobile, robotics, wearables, and beyond.
👋 Hey Product Hunt, I’m Arjun, co-founder of VideoSDK.
I'm beyond excited to launch our Open-Source AI Voice Agent SDK.
Today, voice is becoming the new UI. We expect agents to understand us, respond instantly, and work seamlessly across web, mobile, and even telephony. But, to achieve this, developers have to stitch together: STT, LLM, TTS, glued with HTTP endpoints and, a prayer.
This most often results in agents that sound robotic, hallucinations and fail in product environments without observability.
So we built something to solve that: End-to-End infrastructure to build, deploy, and monitor your AI Voice Agents
Here’s what it offers:
Global WebRTC infra with <80ms latency
Native turn detection, VAD, and noise suppression
Modular pipelines for STT, LLM, TTS, avatars, and real-time model switching
Built-in RAG + memory for grounding and hallucination resistance
SDKs for web, mobile, Unity, IoT, and telephony — no glue code needed
Agent Cloud to scale infinitely with one-click deployments — or self-host with full control
Think of it like moving from a walkie-talkie to a modern cell towers that handles thousands of calls.
VideoSDK gives you the infrastructure to build voice agents that actually work in the real world, at scale.
I'd love your thoughts and questions! Happy to dive deep into architecture, use cases, or crazy edge cases you've been struggling with.
🔥 This is a game-changer for anyone building with voice! Love how you're simplifying the entire stack for real-time Voice AI—especially the flexibility across telephony, web, mobile, and even robotics. Open-sourcing it makes it even more powerful for indie hackers and startups. Huge kudos to the team 👏
Congrats on the launch! 🎉 @Video SDK This looks like a game-changer for voice AI development. The <80ms latency with global WebRTC infrastructure sounds impressive. Quick question - how does your native turn detection handle overlapping speech or interruptions? That's always been a challenge with voice agents. Also curious about the pricing model for the Agent Cloud vs self-hosting options!
@nicoleastor Thanks! 🙌 Super glad you found it interesting. Turn detection handles overlaps smartly in real-time — curious, are you exploring voice agents for a specific use case?
This is a fantastic step toward making real-time voice AI more accessible to developers across platforms. Love that it's open-source — excited to see what the community builds with it! Congrats on the launch 🚀
Video SDK's AI Voice Agent SDK with its low - latency infrastructure and modular pipelines is a great help for developers building real - time voice applications! For developers who want to integrate custom AI models into the SDK, does Video SDK's AI Voice Agent SDK support easy integration of custom models?
@hormold Hey Nikita! VideoSDK provides SDKs for all the platforms for creating virtual meetings & Connecting realtime audio/video to Unity Games, with AI AgentSDK you can connect an AI participant to those sessions, You can checkout our docs to know see all the features that are available
“VideoSDK looks stellar love how it streamlines building real-time video and audio experiences with easy-to-use APIs. what’s next for it? Are you planning upgrades like low-latency streaming, built-in recording, or advanced moderation tools?”
@pulkitgarg Hey Pulkit! Thanks for your support! We already have ILS Steaming with near low latency, Also you can record entire session or individual participant stream easily and store it in any cloud
Replies
Video SDK
👋 Hey Product Hunt, I’m Arjun, co-founder of VideoSDK.
I'm beyond excited to launch our Open-Source AI Voice Agent SDK.
Today, voice is becoming the new UI. We expect agents to understand us, respond instantly, and work seamlessly across web, mobile, and even telephony. But, to achieve this, developers have to stitch together: STT, LLM, TTS, glued with HTTP endpoints and, a prayer.
This most often results in agents that sound robotic, hallucinations and fail in product environments without observability.
So we built something to solve that: End-to-End infrastructure to build, deploy, and monitor your AI Voice Agents
Here’s what it offers:
Global WebRTC infra with <80ms latency
Native turn detection, VAD, and noise suppression
Modular pipelines for STT, LLM, TTS, avatars, and real-time model switching
Built-in RAG + memory for grounding and hallucination resistance
SDKs for web, mobile, Unity, IoT, and telephony — no glue code needed
Agent Cloud to scale infinitely with one-click deployments — or self-host with full control
Think of it like moving from a walkie-talkie to a modern cell towers that handles thousands of calls.
VideoSDK gives you the infrastructure to build voice agents that actually work in the real world, at scale.
I'd love your thoughts and questions! Happy to dive deep into architecture, use cases, or crazy edge cases you've been struggling with.
@arjun_kava1 Design is so sleek and user-friendly!
Video SDK
@1mirul Thanks a lot for your kind words.
@arjun_kava1 very cool! Looking forward to trying out the sdk soon.
Video SDK
@preetraj Thanks a lot, Preet for your kind words.
Video SDK
🔥 This is a game-changer for anyone building with voice! Love how you're simplifying the entire stack for real-time Voice AI—especially the flexibility across telephony, web, mobile, and even robotics. Open-sourcing it makes it even more powerful for indie hackers and startups. Huge kudos to the team 👏
Video SDK
@yash_chudasama Thanks a ton, Yash! 🙌 Glad you loved it — we're excited to see what builders like you create with the Voice Agent SDK! 🚀
this looks promising, makes your main product a full stack video & audio framework for building agents.
Congrats on the launch team!
Video SDK
@theanimeshs Thanks so much! Really appreciate the support! 🙌
Another amazing launch! Let's go team @arjun_kava1 @sagar_kava
Video SDK
@sagar_kava @neelptl2602 Thanks a lot for your support.
Kombai
Congrats on the launch. @arjun_kava1 .
Video SDK
@sourabh_upreti Thanks so much! Appreciate the support 🙌
Tidyread
Congrats on the launch! 🎉 @Video SDK This looks like a game-changer for voice AI development. The <80ms latency with global WebRTC infrastructure sounds impressive. Quick question - how does your native turn detection handle overlapping speech or interruptions? That's always been a challenge with voice agents. Also curious about the pricing model for the Agent Cloud vs self-hosting options!
Video SDK
@nicoleastor Thanks! 🙌 Super glad you found it interesting. Turn detection handles overlaps smartly in real-time — curious, are you exploring voice agents for a specific use case?
Video SDK
Congrats on the launch, team!!! 🥳
For Introducing Voice Agent SDK — an open-source framework to build real-time voice agents that actually work in production.
Built on VideoSDK, it empowers agents to join meetings, listen, speak, and think — all with under 80ms latency.
The cascading pipeline supports STT, LLM, TTS, VAD, and Turn Detection — fully provider-agnostic.
With A2A and MCP, you get multi-agent collaboration and seamless integration with external tools and services.
We can’t wait to see what the community builds with Voice Agent SDK — go create something amazing!
Video SDK
@deep_bhupatkar Thanks so much! Really appreciate the support! 🙌
Congratulations on the launch team. Feel free to import it on LaunchIgniter for maximum visibility
Video SDK
@mjdhameliya Thanks so much appreciate it!
Hi, Arjun and team. Congrats on the launch!
Video SDK
@maksym_skrypka Thanks so much! We really appreciate your support.
Video SDK
@maksym_skrypka Thanks for your support.
Linkinize
This is a fantastic step toward making real-time voice AI more accessible to developers across platforms. Love that it's open-source — excited to see what the community builds with it! Congrats on the launch 🚀
Video SDK
@naderikladious Thank you! We’re thrilled to see the excitement can’t wait to see what you and the community create with it! 🚀
DhiWise
Video SDK
@rahul_shingala Thanks a lot, Chief.
Video SDK's AI Voice Agent SDK with its low - latency infrastructure and modular pipelines is a great help for developers building real - time voice applications! For developers who want to integrate custom AI models into the SDK, does Video SDK's AI Voice Agent SDK support easy integration of custom models?
Congratulations on the launch!
@kbao5 Thanks Karina! Really Appreciate your support
Video SDK
@kbao5 Thank you so much.
I think I saw an SDK that looks almost 1-to-1 like yours and is called LiveKit.
You have a cool product; can you tell me how you differ and how long you've been working on it? Huge scale of work!
@hormold Hey Nikita! VideoSDK provides SDKs for all the platforms for creating virtual meetings & Connecting realtime audio/video to Unity Games, with AI AgentSDK you can connect an AI participant to those sessions, You can checkout our docs to know see all the features that are available
“VideoSDK looks stellar love how it streamlines building real-time video and audio experiences with easy-to-use APIs. what’s next for it? Are you planning upgrades like low-latency streaming, built-in recording, or advanced moderation tools?”
@pulkitgarg Hey Pulkit! Thanks for your support! We already have ILS Steaming with near low latency, Also you can record entire session or individual participant stream easily and store it in any cloud
They are great!!
@tahel_romero Thanks Tahel !, Really appreciate your support
Refrens
Getting that 80ms latency consistently is the key. Kudos for achieving this.
thanks for making it open source!
All the best for today, I’ve been a VoiceDSK customer for years, and the evolution is promising.