Tines The single, secure environment for agents, apps, and automations.
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.
Ota
Congratulations on the launch. Operationally, what’s the difference between scaling inbound versus outbound?
Dograh
@bobaikato - Thank you for your comment.
Inbound volume needs to scale more dynamically and is not in operator's control while outbound volume can be controlled by the operator.
Example: If there is a big event in town, a car dealership might get many more calls than they usually do on a normal days.
So, when it comes to scaling, the inbound needs to be more elastic and responsive, while the scaling requirements for outbound can be preplanned and provisioned.
Dograh
Thats an excellent question @bobaikato
Its mostly around agent building.
In general more receptive about AI agents in inbound calls( e.g. Customer support etc) rather than outbound calls (e.g. Insurance reminder etc)
In outbound we have seen that obsession around getting the first 15 seconds right works best. While in inbound scoping and being abl to handle variety of queries and handoff ecomes critical.
Dograh
@bobaikato Inbound requires elastic capacity because call volume can spike unexpectedly. Outbound is easier to forecast and provision since the operator controls the call volume.
@pritesh_kumar3 This looks very promising. Will users be able to build agents without writing any code
Dograh
@dipanshu_kushwaha5 Thanks for your message.
Yes. 100%. Dograh is to voice agents what @n8n 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.
Dograh
@dipanshu_kushwaha 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.
Dograh
@dipanshu_kushwaha5 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.
FuseBase
Congrats, team! Long-awaited launch! Could you add more built-in observability around latency, token usage, model performance, and call quality?
Dograh
@kate_ramakaieva - Thank you for your message.
Yes, observability and automatic evals creation is something that's on top of our head. We do integrate our basic observability using OTEL exporters on Langfuse, where you can already create data sets for your own use cases.
We are also trying to add these features natively on Dograh and MCP so that observability around latency, token uses, and model performance becomes a first-class citizen of the platform on both Cloud and your self-hosted environments.
Wishing you all the best with @FuseBase
Dograh
@kate_ramakaieva Thanks for the feedback. We’re working toward native observability for latency, token usage, model performance, and call quality across both cloud and self-hosted deployments.
Dograh
@kate_ramakaieva thanks for pushing us in this direction. its definitely a part of our pipeline - and a high priority release
Dograh
@zakiah_hashim - Thank you for your message.
Two things are different - 1. Quality of the audio. Audio over browser is sampled at a higher sample rate compared to telephony - typically at 24k Hz compared to 8k Hz. 2. Signaling - Telephony has a better backbone infrastructure for faster signaling and data routing. It gets lower latency RTT compared to browser.
Dograh
@zakiah_hashim thanks for asking this. You definitely get better audio quality and you can integrate on any web based system (website/app) using our add to website widget in the settings within any agent
Dograh
@zakiah_hashim Thank your for support and question.
Another big practical difference is that the browser call doubles as your test mode. You can try unpublished changes to a bot straight from the dashboard without dialing in or redeploying, which makes iterating much faster.
The other change is how context reaches the agent: on a phone call it comes through the telephony layer(if inbound) or the API trigger, whereas in a web call you inject it yourself via template context variables.
We recently added the ability to simulate call direction (inbound vs outbound) there too, so you can reproduce a real scenario before going live or spending time and extra money on the telephony costs.
Very interesting! Am I correct in understanding that it’s possible to build a voice AI based on your service and make calls worldwide? I need to make reservations by phone.
Dograh
@natalia_iankovych - Yes. Thats correct. You can build voice agents on top of Dograh and make calls worldwide by connecting it with various telephony providers, like Twilio. You can definitely make reservations by phone.
Dograh
Hi @natalia_iankovych - definitley. You can build voice agents using Dograh for global use cases and in 70+ languages
Nas.com
How does the human handoff work when an agent reaches a conversation it cannot confidently handle?
Dograh
@nuseir_yassin1 - Thanks for your message.
We have very excellent support for human handoff, where you can declare static destinations or destinations based on the context from the conversation of the agent with the caller. You can define PSTN phone numbers or SIP addresses or ViciDial Ingroups in those destinations where the voice agent can transfer the call based on your matching conditions.
And, of course, have to prompt the LLM to make that transfer call based on certain conditions. If prompted well, the LLM can do it with very high confidence.
Dograh
Hello@nuseir_yassin1 thank you for your message. Adding to Abhishek's reply - the failure path is worth noting too: if the transfer destination can't be resolved (resolver timeout, no match, etc.), it fails gracefully and the agent keeps the conversation pipeline running rather than dropping the call. And for tightening when it hands off, the QA node surfaces signals like repeats, interruptions, and dead air that teams use to refine the confidence logic over time.
Dograh
@nuseir_yassin1 Dograh can hand off to static or dynamically resolved destinations, including phone numbers, SIP addresses, and ViciDial ingroups. The agent dials the destination and waits for an answer before bridging the caller, with configurable transition messages, timeouts, and fallback behavior if the transfer fails.
Dograh
Thanks @nuseir_yassin1 the human handoff is seamless with Dograh - you can create a separate tool for human transfer and attach this to your voice agent (and instruct it to call it when required)
P.S. really appreciate the comment coming from you Nas :)
is there a marketplace for agent templates?
Dograh
@rahul_dalmia4 - Thank you for your comment.
Not right now. But this is one of the growth engine that we have thought about in the past.
Dograh
Thanks @rahul_dalmia4 . We will be adding templates in the coming weeks - as of now a template marketplace doesnt exist.
Having said that you can create any voice agent template from the agent builder itself in <60seconds. Or even better, we have amazing MCP that can build a ready to go voice agent within minutes.