Product Thumbnail

Daily Bots

Build voice-to-voice AI agents with any LLM with Open Source

API
Open Source
Artificial Intelligence

Build hosted AI agents on Daily Bots, the Open Source cloud for ultra low latency voice and video. Use commercial and open models. Incorporate tool use, telephony, vision, etc. If your needs evolve beyond Daily Bots, run your code anywhere that supports RTVI.

Top comment

Hi Product Hunt! Today we’re sharing Daily Bots, a hosted platform for real-time voice and video AI bots. We built Daily Bots to help developers ship and scale voice and video agents, using Open Source SDKs and deployed on Daily’s global infrastructure. For the past 18 months, we've been experimenting with and building tools for voice-to-voice and real-time video AI. We've helped our customers ship games, meeting co-pilots, medical documentation systems, customer support agents, virtual interviewers, teaching assistants, low-code voice AI platforms, virtual avatar infrastructure, and much more. We love this new world of generative AI and we want to make real-time AI accessible to every hacker, maker, and product team. We've helped create two big Open Source toolkits for real-time AI. Pipecat enables server-side "orchestration" of multi-model, multi-modal AI workflows. And RTVI is an open standard for connecting clients to real-time voice and video inference backends. Daily Bots is built on Pipecat and RTVI. You can build a Daily Bots application using the Open Source RTVI SDKs for Web, iOS, and Android; ship fast and scale quickly on Daily's global WebRTC infrastructure; and retain the flexibility to move to a different platform or run your own infra if you want to in the future. With Daily Bots, you can create AI agents that talk naturally, with fast voice-to-voice response times, interruption support, and multi-turn context management. You can use both commercial and open models. We’ve partnered with Anthropic, Cartesia, Deepgram, and Together AI. (And you can use any other LLM that supports OpenAI-compatible APIs.) Finally, you can buy phone numbers from us and configure your bot to accept dial-in telephone calls. We're excited to see what you build. Let us know what you're thinking about making with Daily Bots. And if you just want to experiment with a few LLMs, prompts, and voices, check out this demo: https://demo.dailybots.ai/

Comment highlights

Hi there, can you incorporate Australian numbers? I am already using one from another company for the first product that works off ChatGPT 4o and I am loving it. Want to try out yours for the second product we'll be launching soon.

I adore how flexible this launch is, the availability of multiple LLMs and free software is a huge bonus.

Though I think it's great that developers can increase productivity with the Daily Bot, I'm interested in how it performs. Playing with these everyday bots is entertaining.

It's a great idea to create AI agents with how latency for speech and video. How the business and freely available source approaches are combined fascinates me. I appreciate you sharing this.

Wow, this is awesome. Thanks for providing this to the community I have a domain called Voice2voice dot ai. I have been thinking about what to hack with this, and you've just made my path a lot easier.🚀

Exciting to see such a robust platform for building voice and video agents! Curious if there are any limitations on the types of models that can be used?

The flexibility to use both commercial and open models is a big plus! Wishing you continued success in making real-time AI accessible to more developers.

The real-time capabilities for voice and video look impressive! Is it possible to integrate with existing telephony systems for a seamless transition?

Hey! It sounds like an exciting opportunity to build more reliable and engaging relationships with customers. I'm intrigued

Hello Daily Bots! 🎉 Congratulations on the launch of Daily Bots! 🚀 Your new platform for real-time voice and video AI bots sounds incredible. With all the hard work you’ve put into developing this over the past 18 months, it’s great to see it come to fruition. I’m curious: How do you envision Daily Bots transforming the landscape of real-time AI applications, and what unique opportunities does it offer for developers looking to integrate voice and video AI into their projects? 🤔🌟 Looking forward to seeing the innovative ways people will use Daily Bots!

Congrats to the whole Daily team on this incredible launch and an insanely cool demo! Love the cutting-edge work you guys are doing with Pipecat and real-time, amazing to see how easy it is to build with this. Can't wait to try this out more myself!

Wow- what an amazing launch! Incredible to see how Daily keeps pushing the boundaries on real-time interactions. Congratulations to the full team!

This is John, a totally normal human person. https://x.com/chadbailey59/statu...

So excited for this! Great job @kwindla and team. There are so many use cases this will open up.

So awesome! We've now built a whole demo on and that was a great experience. Looking forward to sussing out DailyBots before launch. One problem with pipecat was the scalability of the backend was a little wonky (literally just cloning python subprocesses). This feels like it's taken care of more elegantly here? Can someone confirm?