Dograh

Dograh vs Synthflow: Open-Source Code or an Enterprise Contract

Dograh vs Synthflow: Open-Source Code or an Enterprise Contract
ComparisonOctober 24, 2026·9 min read

Dograh vs Synthflow: Open-Source Code or an Enterprise Contract

Vemu Sandeep
Vemu Sandeep·GTM Engineer, Dograh AI

GTM engineer at Dograh working across voice AI and enterprise AI. IIT (BHU) and IIM Visakhapatnam alumnus.

Choosing Dograh vs Synthflow comes down to who runs the platform. Synthflow is closed source and hosted on its own cloud, and it sells one plan, Enterprise, with contracts from $30,000 a year. Dograh, an open-source, self-hostable voice agent platform, runs on your own servers for free or on Dograh Cloud, with any model layer you choose.

Key Takeaways

  • Synthflow sells one Enterprise plan, while Dograh's code is free to self-host.
  • Older Synthflow workspaces get only Synthflow LLM, while on Dograh you choose every model.
  • Both draw calls as nodes, but in Dograh a sub-flow's return is a pathway you draw.

This post is part of our guide to Synthflow alternatives. The guide's section "Dograh: run the platform yourself" gives Dograh one place among eight options. This post sets Synthflow against Dograh, an open-source, self-hostable voice agent platform, row by row, and ends with who should stay on Synthflow.

The two platforms, row by row

Synthflow sells a hosted service under contract, while Dograh is open-source software you can run anywhere.

RowSynthflowDograh
LicenceClosed sourceOpen source under BSD-2-Clause, with the code on GitHub and more than 5,900 stars
Where it runsSynthflow's own cloud, with region-based hosting in the US and EU. But you pick a region, not your own serversYour own servers with Docker Compose, Dograh Cloud, or on-prem and private cloud on Enterprise. But self-hosting puts the servers on your team
How you payOne plan, Enterprise, with contracts from $30,000 a year, scoped by volume, concurrency, telephony and integrations. But even a small pilot starts at that floorSelf-hosted: no per-minute platform fee (servers, model keys and phone minutes still cost). Dograh Cloud: a per-minute platform fee (see below)
ModelsGPT models plus Synthflow LLM, and your own OpenAI or Azure OpenAI key once BYOK access is switched on for your account. But older Pro, Growth and Agency workspaces get only Synthflow LLMDograh's models, your own keys for supported providers, or open-weight models you host
BuilderPrompt Builder or the visual Flow Designer, one mode per agent, with nodes such as Branch, Trigger Subflow and Real-Time BookingA visual workflow builder of nodes joined by pathways, QA that scores each step, and an MCP server for AI assistants
PhoneNative telephony, numbers in the US, Canada and Australia, and tested integrations such as Twilio, Telnyx, Vonage and ZoomYour own carrier, from Twilio and Telnyx to Exotel and Asterisk ARI, or Dograh Managed SIP on Dograh Cloud
Transfer to a personA Call Transfer node that hands the live call to a person or another phone systemTransfer Call on Twilio, Telnyx and Asterisk ARI, with the details written to your system by an HTTP API tool first
HIPAA and certificatesA BAA for customers who switch on its HIPAA Setting, and SOC 2 Type 2, ISO/IEC 27001 and PCI DSS on its trust centerSelf-host inside your own compliance perimeter, so there is no vendor to certify and no BAA with Dograh
Call dataA 30-day auto-delete toggle and PII redaction for transcripts, webhooks and logsSelf-hosted, recordings and transcripts stay on your own storage

How you pay: a contract or a platform fee

Synthflow prices the whole service as one annual contract, while Dograh charges for the platform only, if at all.

Synthflow's pricing page lists one plan: "Enterprise contracts start at $30,000 annually." The final price is "scoped around call volume, concurrency, telephony setup, integrations, security needs, and launch support," and the contract includes implementation, onboarding, testing and launch support. Calls are measured per second, and your exact rates come from your agreement.

Self-hosted Dograh has no per-minute platform fee (servers, model keys and phone minutes still cost); Dograh Cloud has a 1¢-a-minute platform fee. Cloud includes 10 concurrent calls. You can start on either today, with no sales call. Our breakdown of Synthflow pricing works out what the floor means each month and what the same money buys elsewhere.

Who picks the models

Synthflow chooses which models you can use, while on Dograh you choose.

Synthflow's model settings list GPT models from GPT-4o to GPT-6-Luna, plus Synthflow LLM and Advanced Synthflow LLM. "GPT and other third-party models are only available on Enterprise plans", so the older Pro, Growth and Agency workspaces, which Synthflow no longer sells, get only Synthflow LLM. Your own OpenAI key appears only when BYOK access is enabled for your account, and Azure OpenAI can be connected too.

Dograh is the orchestration layer: it runs the call flow, tools and telephony, and the speech and language models are a separate layer you choose. That can be Dograh's own models, your own keys for a supported provider, or open-weight models you host. With your own keys, the audio still reaches each provider. The call audio stays in-house only when the speech and language models run on your own servers too. Our post on the open-source alternative to Synthflow covers that setup.

Building the call: Flow Designer and Dograh

Both platforms draw a call as connected steps, so a team used to one will recognise the other.

In Synthflow, each agent is either a single prompt (Prompt Builder) or a Flow Designer flow, never both. Flow Designer nodes ask questions, speak fixed messages, branch on conditions, run custom actions, book appointments and transfer calls. Trigger Subflow hands the call to a sub-agent and returns to the main flow when it finishes. Synthflow's Workflows, which handle everything around the call, are Enterprise only.

Dograh's visual workflow builder uses a Start Call node, Agent nodes and an End Call node, joined by pathways that each carry a written condition the AI reads. For a sub-flow, you draw one pathway into that part of the workflow and a second one back to the next step, because the return is not automatic. HTTP API tools read and write your systems during the call, and a Webhook node sends the results afterwards.

Two flow builders side by side: in Synthflow a sub-agent returns to the main flow by itself; in Dograh a pathway leads into a sub-flow part and a second, hand-drawn pathway leads back to the next step.
When you rebuild a Synthflow agent in Dograh, mark every Trigger Subflow first. Each one needs a second pathway drawn back to the next step, or the call has no way back to the main steps.

Dograh's MCP server lets an AI assistant create and edit agents, which helps when you rebuild many Synthflow flows. Our guide on how to migrate from Synthflow to open-source voice AI maps each Flow Designer node to its Dograh match.

Dograh

Open Source Alternative to Vapi / Retell

Self-hosted voice agent platform — no per-minute fees

dograh-hq/dograh

Star on GitHub

Phone, HIPAA and call data

Synthflow bundles phone, compliance and data controls into the contract, while Dograh hands each of them to your own setup.

Synthflow's telephony docs describe native telephony, numbers it sells in the US, Canada and Australia, and tested integrations such as Twilio, Telnyx, Vonage and Zoom. Connecting your own SIP trunk or phone system (PBX) needs an Enterprise plan. Dograh connects to your own carrier: Twilio, Vonage, Plivo, Telnyx, Cloudonix, Exotel, Vobiz or Asterisk ARI, or Dograh Managed SIP on Dograh Cloud. Transfer Call works on Twilio, Telnyx and Asterisk ARI. It passes no summary by default; on Twilio it can play a short spoken introduction to both people. Write the details to your system with an HTTP API tool before the transfer.

Synthflow signs a BAA for customers using its HIPAA Setting, which is off by default. For patient calls, self-host Dograh. No BAA with Dograh is needed, because Dograh never sees the data. Your speech and language providers may need their own BAA, and your phone carrier may too. Dograh starts every account on its own managed models. To keep call audio away from Dograh, open Models, switch the Organization default to BYOK with your own speech and language providers (or local models), and check that no agent has its own model override.

On call data, Synthflow's data settings include a toggle that deletes transcripts, recordings and caller IDs after 30 days, and PII redaction for transcripts, webhook payloads and logs. Self-hosted Dograh keeps recordings and transcripts on your own storage. Recordings and transcripts keep whatever is said, so the call never asks for a full account, card or Social Security number; use a short check such as the last four digits, and send payment links by text or email from your own system.

Who should stay on Synthflow

Synthflow is the better fit for some teams, and the reasons are concrete. Stay if you want the vendor to scope, build and launch the agent under one contract, with onboarding and testing inside the price, or if your buyers need certificates on the vendor itself, such as SOC 2 Type 2, ISO/IEC 27001 and PCI DSS v4.0.1. EU processing on a hosted platform with redaction built in is another good reason to stay. Dograh covers the certificate need its own way. Because you self-host Dograh inside your existing compliance perimeter, you don't need a separate vendor review for Dograh.

Agencies have a new reason to look again. Synthflow removed in-product reselling through Stripe on 15 September 2026. Subaccounts and branding still work, but client billing now runs through your own Stripe account or another system. For client billing, Dograh connects to Paygent, which tracks each call's usage and invoices your clients at your own rates.

When Dograh is the stronger fit

Dograh is the stronger fit for teams that want to own the platform, because it answers the gaps that start most searches away from Synthflow.

It is open source under BSD-2-Clause, so you can self-host it today without an annual contract, and self-hosted it has no per-minute platform fee. You choose every model, from your own provider keys to open-weight models on your own servers, and your numbers stay with your carrier. A team used to the Flow Designer gets a nodes-and-pathways builder, with QA that scores each step.

Self-hosting runs on Docker Compose and puts uptime and updates in your team's hands. Teams weighing a hosted platform with self-serve plans will find the same trade in our Dograh vs Bland AI comparison.

Run your real call script on both over a phone line, since most phone calls still reach the agent as 8 kHz audio while a browser demo runs at 16 kHz. To try Dograh, self-host it from GitHub with Docker Compose, or start on Dograh Cloud.

Join the Dograh Community

Dograh is an OSS alternative to Vapi. Join our Slack community for queries, releases, best practices & community interactions.

Glossary

Flow Designer
Synthflow's visual call builder, where each node handles one part of the call and branches decide where it goes next. Each Synthflow agent uses either the Flow Designer or a single prompt, never both.
Trigger Subflow
A Flow Designer node that hands the call to a sub-agent and returns to the main flow when the sub-agent finishes. In Dograh the same shape is two pathways, one in and one drawn back.
Bring your own key (BYOK)
Using your own account with a model provider instead of the platform's. You hold the contract and the bill, but the call audio still goes to that provider.
Open-weight model
An AI model whose weights you can download and run on your own servers. Hosting one is the only way to keep call audio from reaching an outside model provider.

Frequently Asked Questions

Get started with Dograh

Build, deploy, and scale AI agents with Dograh. Join the community of developers building the future.