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
this is not even open source and the license is proprietary. Why were you lying?
The star has been sent
Can we connect ?
dope
how do you connect client # to this
Is there $$ for tts or how does it call for free?
you look like a famous comedian actor!
How does it fare against Gemini Live Preview API
own fork Pipecat minio, Cloudflared dependency, old coturn looks promising xD
I manages to squeeze Whisper onto an 8GB Jetson Orin Nano if anyone wants it. Local, free and very good quality
This was very informative, appreciate it.
Great, but what about the telephony setup? How are you handling this? Which providers, specially in the world wide context?
Livekit is great is MIT licensed you can self host
that woul be awesome with Hermes Agent ;)
Developers Finally Got an Open-Source Voice AI Platform (Dograh). Thanks
What about text-to-speech that lets you define the voice, give it emotion attributes, individual actor prompts, and plug in a novel to convert?
This is the worst possible application for AI, nobody wants to receive spam phone calls made by AI, nobody wants to talk to an AI for customer support
Let's be real: this isn't 'control,' it's just a fancy wrapper. You're not escaping platform fees; you're just swapping one subscription for three separate API bills from OpenAI, ElevenLabs, and Deepgram. Calling a wrapper over proprietary APIs 'full control over your infrastructure' is a bold marketing claim. Self-hosting a UI that still relies on closed-source clouds is just an illusion of control. True open-source freedom would mean native integration with local stacks like Ollama, whisper.cpp, or Piper. Without that, it's not a sovereign AI platform -it's just a visual dashboard for paying other people's API bills.
In the middle of the video bro become AI avatar
add in foreign languages and problems increase massively. Whisper large models on more exotic languages are rubbish. Thank Fk for virtual audio Cable. How does this handle other languages?