Audio & voiceDocumented overviewLast checked Sep 29, 2026

Dograh: Pricing, Features & Best Use Cases

Open-source, self-hostable voice AI agent platform with a drag-and-drop workflow builder, positioned as an alternative to Vapi and Retell.

Who should use Dograh

Choose Dograh if you want to build phone voice agents with a drag-and-drop workflow on infrastructure you control, either self-hosted for free or hosted from 1 cent per minute with your own provider keys. Based on the vendor's documentation, not on a hands-on test.

Best for: Developers building custom voice agents

Also a good fit for

  • Companies with data-residency or compliance requirements
  • Teams wanting an OSS alternative to Vapi or Retell

Consider another tool if hosted plan includes only 10 concurrent calls by default

Or if

  • BYOK: model and telephony provider costs are billed separately
  • LLM swapping for self-hosted models is still in beta

Dograh pricing and usage limits

Prices checked Sep 29, 2026 on the official US pricing page. Official pricing ↗ Prices and limits change often.

Dograh pricing page with plans and prices — screenshot of the audio & voice AI tool, Oct 1, 2026
The official Dograh pricing page as we saw it. dograh.com, captured Oct 1, 2026

Free access and trial conditions

Open-source edition is free forever, self-hosted.

Self-serve credits start at $5.

Paid plans: what changes as you upgrade

Open Source self-hosted

Free source (opens in a new tab)

Unlimited

For: Teams that can self-host

Limits

  • You operate the infrastructure

Includes

  • Full platform, no limits
  • Your own API keys
1 more
  • Auditable source

API included

Pay as you go web

$0.01 source (opens in a new tab)

Usage

For: Starting in minutes without hosting

Limits

  • 10 concurrent calls included
  • Self-serve credits from $5

Includes

  • BYOK or Dograh Models
  • Top up anytime

API included

Custom volume web

Custom pricing source (opens in a new tab)

Custom

For: High call volume

Limits

  • Committed monthly volume

Includes

  • Volume discounts
  • Priority support via email, Slack, WhatsApp

API included

Enterprise (on-prem) self-hosted

Custom pricing source (opens in a new tab)

Custom

For: Regulated industries

Includes

  • On-prem or private cloud
  • SSO/SAML and audit logs
1 more
  • Dedicated account manager and SLAs

API included

Usage caps, credits and extra costs

LLM, STT, TTS and telephony provider bills under BYOK, or Dograh Models usage pricing.

Not stated.

What is Dograh, and how does it work?

Dograh is an open-source platform for building voice AI agents, presented as a self-hostable alternative to Vapi and Retell. A drag-and-drop workflow builder lets you compose agents from your choice of speech-to-text, LLM, text-to-speech and telephony providers, or switch the whole pipeline to speech-to-speech models such as Gemini Live or GPT Realtime. Integrations listed include OpenAI, Gemini, Groq, Deepgram, ElevenLabs, Cartesia, Twilio, Telnyx, Plivo and Vonage. The full platform can be deployed with Docker on a local machine, a server, on-prem or inside your own VPC so calls, recordings and transcripts stay within your perimeter. Dograh also ships an MCP server so Claude Code, Cursor and other agent runtimes can create and deploy voice agents from the IDE, and offers a hosted cloud with pay-as-you-go pricing.

Dograh homepage — screenshot of the audio & voice AI tool, Oct 1, 2026
Dograh's official site: how the product presents itself. dograh.com, captured Oct 1, 2026

What you provide and what you get back

How Dograh works: what you provide, where it runs and what you get backYOU PROVIDEYour inputAgent workflow designProvider API keysPhone numbers and scriptsAUDIO & VOICEDograhWebfrom $0.01 (Pay as you go)free tier availableaccount requiredchecked Sep 29, 2026YOU GET BACKThe resultInbound and outbound voice agent…Transcripts and recordingsDeployed agentsinput → Dograh → output · from the vendor's own pages, no hands-on test unless stated
What you give Dograh and what comes back, from its documentation

You provide

  • Agent workflow design
  • Provider API keys
  • Phone numbers and scripts

You get back

  • Inbound and outbound voice agent calls
  • Transcripts and recordings
  • Deployed agents

Where you can use it

Platforms
Web
Account
Required
Modes
Cascade STT-LLM-TTS or speech-to-speech
Telephony
Twilio, Telnyx, Plivo, Vonage, Cloudonix, Asterisk
Deployment
Cloud, self-host, on-prem
Languages
70+ in speech-to-speech mode

Best use cases for Dograh

Scenarios are worked out by our editors from the documentation; the actual result depends on your input and plan.

Building inbound and outbound phone voice agents

Who
Developers building call agents
You provide
Workflow, scripts and telephony provider
Expected result
Inbound or outbound phone agent
Plan needed
Pay as you go
Limitation
10 concurrent calls by default source (opens in a new tab)

Running voice AI on-prem for regulated industries

Who
Regulated companies
You provide
Self-hosted deployment
Expected result
Voice AI where calls and transcripts stay in your perimeter
Plan needed
Open Source or Enterprise
Limitation
You run the infrastructure source (opens in a new tab)

Mixing pre-recorded human voice clips with TTS for collections or reminders

Who
Collections and reminder teams
You provide
Pre-recorded voice clips plus TTS
Expected result
Calls mixing human clips with generated speech in one cloned voice
Plan needed
Any
Limitation
Needs recorded clips source (opens in a new tab)

Dograh features and their limits

Dograh homepage — screenshot of the audio & voice AI tool, Oct 1, 2026
Feature overview on the official site. dograh.com, captured Oct 1, 2026

Drag-and-drop workflow builder for voice agents

Composes agents in a drag-and-drop workflow builder Design call flows visually

Access: All editionsLimit: Complex logic may still need webhooks source (opens in a new tab)

Swappable STT, LLM, TTS and telephony providers

Lets you swap STT, LLM, TTS and telephony providers Avoid vendor lock-in

Access: All editionsLimit: Provider costs billed separately source (opens in a new tab)

Speech-to-speech mode via Gemini Live or GPT Realtime

Runs speech-to-speech with Gemini Live or GPT Realtime Lower latency and natural turn-taking

Access: All editionsLimit: Depends on third-party model source (opens in a new tab)

On-prem / VPC deployment with air-gapped model serving

Deploys on-prem or in a VPC with air-gapped model serving Keep calls and PII in your boundary

Access: Open Source and EnterpriseLimit: LLM swapping for self-hosted models is beta source (opens in a new tab)

Dograh: strengths and limits

Where Dograh is strong

  • Fully open source and free to self-host with no feature limits No license cost if you self-host documented source (opens in a new tab)
  • Hosted cloud starts at a 1¢/min platform fee with $5 minimum credit top-up Cheap to start hosted documented source (opens in a new tab)
  • Docker-based local setup documented for macOS, Linux and Windows Easy to try on a laptop documented source (opens in a new tab)
  • Broad list of model and telephony provider integrations You can swap providers as prices or quality change documented source (opens in a new tab)

Limitations to check before paying

  • Hosted plan includes only 10 concurrent calls by default Large call centers need to contact sales documented source (opens in a new tab)
  • BYOK: model and telephony provider costs are billed separately Total cost depends on providers documented source (opens in a new tab)
  • LLM swapping for self-hosted models is still in beta Some self-hosted LLMs not production-ready documented source (opens in a new tab)
  • Anonymous telemetry is on by default in self-hosted installs (opt-out flag) Usage data is sent unless you opt out documented source (opens in a new tab)

How to use Dograh for building a phone voice agent

Set up Dograh

  1. Sign up at app.dograh.com or run the Docker setup from the docs
  2. Add your STT, LLM, TTS and telephony provider keys (or use Dograh Models)
  3. Add credits (from $5) if using the hosted plan

Example: building a phone voice agent

  1. Open the workflow builder and add a greeting node
  2. Connect your LLM and set the call goal
  3. Link a Twilio or Telnyx number
  4. Place a test call and review the transcript

Review and export the result

  1. Confirm the agent follows the scripted flow on a test call
  2. Check credit or provider usage matches expected minutes
Example prompt suggested by our editors (not a recorded output of the product)
Build an AI calling agent that reminds customers about upcoming payment due dates and offers to reschedule.

Dograh API

Dograh pricing page with plans and prices — screenshot of the audio & voice AI tool, Oct 1, 2026
Plan comparison on the official pricing page. dograh.com, captured Oct 1, 2026

API access and separate billing

Dograh has no public API in its official documentation. MCP server lets Claude Code or Cursor build agents; public REST API not confirmed API documentation ↗

Privacy, data use and commercial rights

Summarized from the vendor's current policies; this is not legal advice and a vendor's badge is not an independent audit.

How your inputs and outputs are handled

Self-hosted: calls, recordings and transcripts stay in your perimeter.

Vendor says data is never trained on in the on-prem setup

Commercial use and plan restrictions

Open source

On-prem and audit logs on Enterprise

Controls for business users

  • SSO/SAML
  • Audit logs
  • Data residency

Dograh alternatives by need

"Better suited" is based on documented features and pricing, not on a head-to-head test.

ElevenLabs: better suited to

n8n: better suited to

Make: better suited to

Zapier: better suited to

Alternatives
AlternativeWhen to choose itPricingLimitation
ElevenLabs——Compare
n8n——
Make——
Zapier——

Explore Dograh further

If you are looking at Dograh

Dograh user reviews

No user reviews yet.

Used Dograh? Be the first to share your experience.

Write a review

Reviews are checked by a moderator before they appear. Your email is never published. Plain text only.

Your rating (required)

Show what you made or what went wrong. Images are published only if the review is approved; location data is removed.

    Dograh FAQ

    Is Dograh free?

    The open-source edition is free forever to self-host with no feature limits; the hosted service charges 1 cent per minute. source (opens in a new tab)

    How many concurrent calls does hosted pay-as-you-go allow?

    10 concurrent calls are included; contact Dograh for more. source (opens in a new tab)

    What is the minimum top-up?

    Self-serve credits start from $5 and can be topped up anytime. source (opens in a new tab)

    Can I use my own AI providers?

    Yes, BYOK is supported, or you can use Dograh Models with usage-based pricing. source (opens in a new tab)

    Can coding agents build voice agents with Dograh?

    Yes, Dograh ships an MCP server that Claude Code, Cursor or other MCP clients can use to create and deploy agents. source (opens in a new tab)

    Sources and review methodology

    Official sources and verification dates

    Not verified: Dograh Models pricing; Privacy policy text.

    How we documented and maintain this page

    Every fact about Dograh above comes from the 3 official pages listed here, last compared on Sep 29, 2026; we have not run Dograh ourselves, so it has no editorial score. How we check and re-check pages.

    Article updated Oct 10, 2026; prices checked Sep 29, 2026. Outbound links to vendors are plain links; we do not earn commissions. How we review · Report an error