Harry789

cross-posted from: https://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: https://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: https://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

---

cross-posted from: https://lemmy.world/post/45470250

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.

https://github.com/dograh-hq/dograh

(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 :)

https://github.com/dograh-hq/dograh

Docs: https://docs.dograh.com/

Tech stack if anyone's curious: FastAPI, Next.js, forked Pipecat, Langfuse.

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.

https://github.com/dograh-hq/dograh

(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 :)

https://github.com/dograh-hq/dograh

Docs: https://docs.dograh.com/

Tech stack if anyone's curious: FastAPI, Next.js, forked Pipecat, Langfuse.

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.

https://github.com/dograh-hq/dograh

(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 :)

https://github.com/dograh-hq/dograh

Docs: https://docs.dograh.com/

Tech stack if anyone's curious: FastAPI, Next.js, forked Pipecat, Langfuse.