Dograh
The open source VAPI alternative
Start new thread

Dograh - The open source VAPI alternative

by•
Closed voice platforms make you rent your own agents. Dograh is completely open source- nothing is gated. Visual flow builder, add your model key across 30+ integrations or use local models, telephony, human transfer, and advanced QA & monitoring - all free to self-host in one command. Also connect your claude code with MCP to build voice agents for a use case or call recordings.

Add a comment

Replies

Best

Great launch team. Kudos!

In the meantime, Id love to know how to catch an agent that gives a bad response. And what does the debugging experience look like if we are tryin to figure out why. ?

Maker

 - Thank you for your support.

You can use native QA node in Dograh or integrate with our partner services like Tuner, Noveum or Roark to catch a agent that is not doing its job properly and giving a bad response.

You can use chat mode on Dograh to debug and test an agent while building it.

We are always available on Slack to answer any questions you might have. :)

Maker

 Use Dograh’s native QA node to flag bad responses, then test and debug the agent in chat mode.

  Im actually going to try dograh

Maker

@mayurmaheshwari Great to hear! Let us know if you have any questions while trying it.

Congratulations. And happy product launch.

Maker

 - Thank you so much for your comment. Good luck with ❤️

Maker

Thanks for the support   

Maker

thanks  for your support :)

Maker

@huisong_li Thanks for the support! Wishing you and HarnessRouter all the best. ❤️

Have heard good reviews about Dograh. Also rooting the founders personally being from IITD.

Maker

 - Thanks a lot for your support. ❤️

Please do not hesitate to reach out if you need any support in implementing Voice AI for your use cases.

Maker

Hi  thats such a lovely remark. Would love to connect on other platforms as well . we love IITD :)
Here's lin:

Maker

Thanks for the support! Really appreciate you rooting for Dograh and the founders. ❤️

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

 This means a lot, genuinely. Thanks for sticking with us these past few months :)

Maker

Thanks Bruce! Glad to hear Dograh and our support have been useful.

Maker

 - Thanks a lot for your kind words ❤️

You will always find us here trying to evangelise and promote Open Source voice AI adoption. You will always find help on our Slack Community.

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

Maker

 Thanks for your message.

Yes. 100%. Dograh is to voice agents what is to workflow automation. You can either decide to visually build voice agent using Dograh UI or you can use MCP tools offered by Dograh (cloud or self hosted) to talk to your coding agents to build an agent for you. And all of these play really well with various telephony providers so you can go to production with least friction.

Maker

Yes, you can build voice agents visually in Dograh without writing code. You can also use Dograh’s MCP tools with coding agents if you prefer.

Maker

 To add one more layer - it's no-code even after you build. There's a Test Chat mode where you can edit or replay any turn in a past conversation and Dograh regenerates the agent's replies and node transitions from that point, so you can debug and refine logic without touching code. Makes it easy for non-technical folks (support/ops teams) to actually own the agent long-term, not just the initial build.

Product looks amazing. Congratulations to the team!

Maker

 - Thanks a lot for your support.

Wishing you loads of success and luck with

Maker

Thanks  . lovely to see you rooting for us

Maker

Thanks for the support! 🙌

Maker

 Thank you. Rooting for

Congrats on the launch. Super cool product.

Maker

 - Thank you so much for the support.

We are always hungry for the feedback. Please let us know if you get a chance to try out

Maker

 Thanks a lot.

Maker

Thanks for the support! Glad you liked Dograh.

Maker

thanks  . glad to you found it great

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 )

Maker

 Thank you for your message.

These are some very relevant questions. We connect over Websocket for TTS and STT, so any failure over websocket connection is automatically retried. For LLMs, we have fallbacks in place, so that if our primary LLM takes longer to respond or fails to respond, there are fallback LLMs in place.

I welcome you to try out

Maker

 WebSocket failures for STT and TTS are retried automatically, while LLM timeouts or failures trigger fallback models.

congratulations on the launch. Good product for enterprises who want to self hosted voicebot.

Maker

 - Thanks a lot for your support.

Wishing you all the best for

Maker

Thanks for the support! Glad the self-hosted approach resonates.

Maker

 Absolutely. Self hosting capability is one of our core priorities. Thanks for the support. All the very best for !

The ability to run local models and avoid per-min platform fees is huuuge. But what's best is that the founders are incredibly knowledgeable and always willing to help with setup, best configs or answer any kind of questions. Excited to see where this is going!!

Maker

 - Thanks a lot for your kind words ❤️ Wishing you loads of luck with

Maker

Thanks for the support! Glad the local model support and hands-on help have been useful.

Maker

 the founder shoutout is so real, can confirm from the inside :) and it's not just the founders either - our Slack community's got contributors and users constantly trading configuration insights, figuring out the right tool setup for specific use cases, and helping each other debug.

Maker

Thanks  . lovely to see you root for us :)

First
Previous
1234
Next