from Harry789@lemmy.world to selfhosted@lemmy.world on 17 Apr 13:16
https://lemmy.world/post/45721900
cross-posted from: lemmy.world/post/45721589
Hi All, It has been while,
Dograh is an open-source, self-hostable voice AI agent platform. Think n8n but for phone calls. Visual workflow builder, inbound and outbound calling, bring your own LLM, STT, and TTS.
GitHub: github.com/dograh-hq/dograh
Setup
one command with Docker, about 2 minutes. No signup or API keys needed to get started:
What is new
Pre-call data fetch. Hit your CRM, ERP, or any HTTP endpoint during call setup and inject the response into your prompts. The agent greets the caller by name, references their account status, skips the “can I get your customer ID” step. Configure a POST endpoint in the Start Call node - API key, bearer, basic, or custom header auth supported. 10-second timeout; if the endpoint fails, the call continues without the extra context. Reference fetched values anywhere in prompts with {{customer_name}} syntax.
Pre-recorded voice mixing. Drop in actual human recordings for the predictable parts - greetings, confirmations, hold messages - and let TTS handle only what needs to be dynamic. The greeting sounds human because it is. Latency goes down, TTS costs go down.
Speech-to-speech via Gemini 3.1 Flash Live. One single streaming connection replaces the separate STT, LLM, and TTS hops. Turn response latency drops noticeably and the conversations feel more natural.
Post-call QA with sentiment analysis and miscommunication detection. Full per-turn call traces via Langfuse.
Tool calls, knowledge base, variable extraction are all there too.
What is coming
Real-time noise separation for live call streams - still the thing I most want to solve after last week’s thread. BSD-2 licensed.
GitHub: github.com/dograh-hq/dograh
Special thanks to this community that supported me with my last post ❤️
Happy to get feedback and contributors. A star would mean a lot
#selfhosted
threaded - newest
Wow. Fuck this.