Dograh: The Open-Source Voice AI Platform That Could Kill Your VAPI Bill
If youâre building voice AI applications, youâve probably felt the sting of per-minute SaaS pricing from platforms like Vapi or Retell. A few hundred test calls during development, a demo that runs long, and suddenly youâre looking at a bill that makes you question your life choices.
Enter Dograh â an open-source, self-hostable voice agent platform that promises unlimited voice agents for exactly $0.
What Is Dograh?
Dograh is a drag-and-drop voice agent builder that you can run on your own infrastructure. Itâs BSD 2-Clause licensed (the same license as FreeBSD), which means you can use it commercially, modify it, and distribute it without worrying about copyleft requirements.
The pitch is simple: from zero to a working voice bot in under 2 minutes.
curl -o docker-compose.yaml https://raw.githubusercontent.com/dograh-hq/dograh/main/docker-compose.yaml && \
REGISTRY=ghcr.io/dograh-hq docker compose up --pull always
Thatâs it. Open http://localhost:3010 and youâre building voice agents.
Why This Matters
Hereâs the honest comparison that caught my attention:
| Feature | Dograh | Vapi | Retell |
|---|---|---|---|
| License | BSD 2-Clause | Proprietary | Proprietary |
| Self-hostable | Yes | No | No |
| Pricing | Free (self-host) | Per-minute | Per-minute |
| Bring your own LLM/STT/TTS | Any provider | Their integrations | Their integrations |
| Source customization | Full access | None | None |
| Data residency | Your infra | Their cloud | Their cloud |
The kicker: no vendor lock-in. If Dograh disappears tomorrow, you still have the code. If Vapi triples their prices, youâre stuck renegotiating or rewriting.
Key Features
Zero-config start: Ships with auto-generated API keys and its own LLM/TTS/STT stack. Connect your own keys later if you want.
Telephony built-in: Twilio, Vonage, Vobiz, Cloudonix integrations out of the box. Transfer calls to human agents when the bot gets stuck.
Test mode: Try your agent end-to-end before publishing, with no production calls affected. Make web calls directly from the dashboard while building.
QA Node: A workflow node that analyzes prompt quality across your other nodes. Itâs like having a second pair of eyes on your prompts.
AI Personas for Testing: This is clever â Dograh ships with AI personas that mimic real customers to test your bots. No more asking your coworker to pretend to be an angry customer for the fifth time today.
Whoâs Behind It?
Built by YC alumni and exit founders. They claim to be âcommitted to keeping voice AI openâ â time will tell, but the BSD license is a strong signal. They canât rug-pull the open-source version.
When Would You Use This?
Good fit:
- Youâre building voice agents and want to control costs
- You need data residency (healthcare, finance, government)
- You want to customize the underlying code
- Youâre prototyping and donât want to burn through per-minute credits
Maybe not:
- You need enterprise SLAs and support contracts
- Youâd rather pay than maintain infrastructure
- Youâre building a quick demo and donât care about long-term costs
The Catch?
Self-hosting isnât free in the âzero effortâ sense. You need to run Docker somewhere, handle updates, and debug issues yourself. The community Slack seems active, but you wonât get a support ticket escalation path.
Also, first startup takes 2-3 minutes to download all images. Not a dealbreaker, but worth knowing.
Bottom Line
Dograh looks like a serious contender in the voice AI space. The BSD license, self-hosting option, and bring-your-own-everything approach make it worth evaluating if youâre currently paying per-minute for voice agent infrastructure.
For clinical trial screening, patient intake, appointment scheduling â anywhere youâre running voice agents at scale â the math gets compelling fast.
Links:
- GitHub: github.com/dograh-hq/dograh
- Docs: docs.dograh.com
- Cloud version: app.dograh.com
- Community Slack: Join here