cross-posted from: https://lemmy.world/post/45470185
Hi everyone!
Dograh is an open-source, self-hostable voice AI agent platform. It lets you build phone call agents with a drag-and-drop workflow builder. Think n8n but for voice calls. It’s an alternative to Vapi, Retell, etc.
(Any star would mean a lot - super appreciated ⭐️)
We’ve been building this for about 6 months now, just me and my co-founder. Fully bootstrapped and we have said No to inbound VC money to stay that way. It’s been exciting but also exhausting, we’re getting 5-10 tickets a day now and still figuring out how to keep up with that while shipping new stuff.
Here’s what’s new in v1.20:
- Speech-to-Speech via Gemini 3.1 Flash Live. Instead of stitching together separate STT, LLM, and TTS services, this collapses the whole pipeline into a single connection. The calls sound noticeably more natural.
- Pre-recorded voice mixing. You use actual human voice recordings for predictable parts of the conversation (greetings, confirmations, hold messages) and TTS only kicks in when the agent needs to say something dynamic (use cloned or same voice as fallback) . Saves a lot on TTS costs but most importantly makes bot sound human (because its actual human voice) and lowers latency
- Post-call QA with sentiment analysis and miscommunication detection.
- Full call traces via Langfuse Apart from the above key highlights, we have all the basic stuff: tool calls, call transfer, Knowledge base, etc. Docker setup takes about 2 minutes. Bring your own API keys, no vendor lock-in.
**What’s on the roadmap (happy to hear more requests):" **- Full support for self hostable open source AI models (LLM TTS STT S2S)
- More integrations. Happy to take suggestions here One clarification since I know this community cares about this stuff:
- Dograh is BSD-2 licensed and always will be. No bait and switch. Everything we build goes into the open source.
Just trying to build something useful and keep the lights on. If you can check it out and give us a star it would be a blessing ❤️ , but if not, I love you anyway :)
Docs: https://docs.dograh.com/
Tech stack if anyone’s curious: FastAPI, Next.js, forked Pipecat, Langfuse.
Hello There. I am one of the maintainers of Dograh. Please let me know if you have any questions regarding Voice AI Agents/ Self hosting Language Models/ Speech to Speech live models in general. Looking forward to hearing from you all. Thanks!