Dograh

As a CTO/Solution Architect, I checked how Dograh delivered the outcome and am very happy with them. Best of luck.

How is the latency handled for cascaded systems- for the TTFB - end to end (user stops and then heard the first chunk audio) from lets say one of the many api calls during a 10 turn conversion- 30 api calls to each endpoint - stt, llm , tts - if one of the api calls fails lets say turn 5, sst failed ( null or later then 500 ms response), how your framework is handling 1. Fallback model 2. Retry with same model ? Including edge cases for streaming response error for all the three nodes ( stt, llm , tts )

@pritesh_kumar3 @sandeep_vemu @a6kme1 love the mission behind creating wildly applicable open source offerings. Maybe its an odd question but I am curious - what is the pathway toward revenue generation - is the goal to primarily capture some big fish on the enterprise side? Anyways - killer launch - big fan of what you're doing - following the product / following along!

Let's goo!

Congratulations on the launch @sabiha_khan4 ! Curious to know which major sectors you’re seeing initial traction in. Also, are there any limitations around regional languages or specific geographies?

Congrats on the launch. Super cool product.

🚀 MID-DAY UPDATE: Big thanks to @nuseir_yassin1 We’re having an incredible launch day, and we want to give a massive shoutout to Nuseir Yassin (Nas Daily) for stopping by our thread with some sharp questions on voice orchestration!For anyone following along or asking similar questions about building production-ready AI voice agents with Dograh: • Seamless Human Handoff: Native escalation and live-agent takeover protocols so your voice agents fall back safely whenever human intervention is needed. • Bring any Models & Telephony: Easily swap between underlying ai models and telephony providers without changing your stack. • Developer-First & Open Source: Built by devs, ex CTO's , YC alum - we live and breathe technology and open sourceDrop any technical questions below and we’ll answer them live! ⚡

congratulations 🎉 on the launch, much need

As vapi has become expensive!

Product looks amazing. Congratulations to the team!

Congrats, team! Long-awaited launch! Could you add more built-in observability around latency, token usage, model performance, and call quality?

Open source voice agents with this much flexibility is 🔥 The fact that you can self-host, use local models, and connect Claude Code via MCP makes this especially interesting. Congrats on the launch! 🚀

Congrats on the launch. Can teams customize the QA metrics and scoring rules for different industries or call types?

How does the human handoff work when an agent reaches a conversation it cannot confidently handle?

The ability to bring your own model keys across 30+ integrations makes this feel much more developer-friendly.

Great product!

@pritesh_kumar3 This looks very promising. Will users be able to build agents without writing any code

Hey guys, congratulations on the launch! Curious to know how are you guys priced compared to Vapi or Retell.

Been using Dograh for a few months now, it’s a really awesome product, and support from the team has been great!

Hey Product Hunt, I'm Pritesh, one of the makers of Dograh.Dograh is an open source platform for building voice AI agents - calling agents that answer calls, book appointments, qualify leads, or run payment reminders over the phone.Here's the problem we kept hitting. AI is getting locked up. Closed platforms make you rent your own agents on their cloud, at their price. And right now big labs are lobbying to restrict open source AI itself. We run on one belief: no company should own voice AI.So from day 0 we open sourced every line. BSD-2 license, one command to install, nothing held back, nothing gated. Everything runs on your own server, and it's yours. You build phone agents and also own the whole stack.That is the difference. There is no platform to rent here. No per-minute fee, no gated tier. Bring your own keys, or run local models completely offline, even air-gapped. And it's MCP native - connect Claude Code and build a voice agent by chatting with it.Inside you still get everything the closed platforms sell:Visual flow builder - no glue codeReal time speech to speech - 70+ languages with mid-call switchingTelephony + warm handoff to a humanCall recordings with automatic QAFree REST APIWhy that matters:The payoff is ownership - your only cost is your model billYour data never leaves your servers - compliance gets simpleNo glue code - you ship in hoursIt fits developers and agencies building agents for clients or their internal use case, and compliance-heavy teams in healthcare, finance, and collections. Common uses today include appointment booking, lead qualification, support lines, payment reminders.We are a small team. A star on GitHub or honest feedback here does more for us than you would think.Install it, break it, tell me what's missing. I'm here all day.But first, try a Dograh voice agent now.