In this video, we look at Dograh, an open-source voice AI platform for developers that gives you a Vapi-style visual workflow builder with self-hosting, provider choice, recordings, testing, and control over your infrastructure. We’ll look at why voice AI agents are not just “ChatGPT with a phone number,” how costs stack up across speech-to-text, LLMs, text-to-speech, telephony, and platform fees, and why developers may want an open-source alternative to hosted tools like Vapi, Bland, and Retell. 🔗 Relevant Links Dograh Repo - https://github.com/dograh-hq/dograh Self-host with Docker - https://docs.dograh.com/deployment/docker Dograh - https://app.dograh.com/ ❤️ More about us Radically better observability stack: https://betterstack.com/ Written tutorials: https://betterstack.com/community/ Example projects: https://github.com/BetterStackHQ 📱 Socials Twitter: https://twitter.com/betterstackhq Instagram: https://www.instagram.com/betterstackhq/ TikTok: https://www.tiktok.com/@betterstack LinkedIn: https://www.linkedin.com/company/betterstack 📌 Chapters: 0:00 - Stop Renting Your Voice AI Stack 0:26 - Why AI Phone Agents Get Expensive Fast 1:00 - Voice AI Is Not Just ChatGPT With a Phone Number 1:29 - Dograh Demo: Build a Voice AI Agent Locally 1:57 - Creating a Lead Qualification AI Phone Agent 3:36 - What Is Dograh? Open-Source Voice AI Platform Explained 4:11 - Voice AI Agent Workflow 4:35 - Testing, Tracing, Recordings, Analytics, and Deployment 4:47 - Vapi, Bland, and Retell: Fast but Less Control 5:23 - Pipecat and Vocode: Flexible but More Glue 5:50 - Where Dograh Fits for Devs
ADVERTISEMENT
Have tried them out. Probably the best open source voice platform out there.
that woul be awesome with Hermes Agent ;)
U know about livekit and pipecat ?
Completely irrelevant to what i work with and yet super excited to see this exists. I love how this channel does real research on tools like these.
Voice AI is so exciting! Thank you for this.
bro that AI generated animations in your videos looks literal shitt. i remember i used to get excited to see your new videos... not anymore!
Developers Finally Got an Open-Source Voice AI Platform (Dograh). Thanks
Thank you. We want more videos like this
This is exactly I was looking for. Thanks for sharing
Awesome video. Thanks for creating this. Voice AI is ecosystem is fragmented, and we need more content like this in the developer ecosystem to distil signal from noise.
You guys keep finding gems. Excellent work.
Great, but what about the telephony setup? How are you handling this? Which providers, specially in the world wide context?
2:55 Why the gaslighting? That is video playback you're talking over. You did not say, "Yes, I'm here." Why lie??!
looks interesting, need to give it a try!
part of their open source community. They are shipping fast.. worth a try if anyone is building on pipecat themselves.
does this app uses Asterisk software for calls or else how else can we connect real time calls here in this
I manages to squeeze Whisper onto an 8GB Jetson Orin Nano if anyone wants it. Local, free and very good quality
Would this work for a voice assistant?
Talking about voice, your voice sounds sooo artificial, maybe some strong noice filter or something. I rather listen to a bit of noise than this. It makes my mind evaluating all the time if I'm watching a real human or AI generated video. And it's not only this video, I've noticed it some time ago.
Building any voice agent without live kit might be a bad choice