automation

dograh: Automate Voice AI

Name: dograh: Automate Voice AI
Author: dograh-hq

Self-hosted voice AI platform for founders, with 4.1k+ GitHub stars. Automate speech tasks with ease.

intermediate⏱ 30 minutes💵 Free + LLM API costs

5,037 stars1,173 forksPythonQuality 8/10Updated 7/27/2026100% free · open source

What it is

Build voice AI automations on your own servers with an open-source, self-hosted platform.

What you can make with it

Automations that can answer incoming phone calls, route tasks to employees, or send automated voice messages.

How it helps

Dograh lets you build custom voice experiences without relying on cloud-based services, giving you control and flexibility.

Real use case example

"A founder uses Dograh to create a custom voice AI that answers customer support calls, directs them to the right team member, and saves all the call details to their CRM."

If you're new

You can pick this up when you're familiar with basic programming concepts and want to explore voice AI without diving into complex cloud services.

If you're senior

Senior engineers and professionals will reach for this when they need to build custom, on-premises voice AI solutions for their organizations.

Common confusion cleared up

Don't worry if you don't have extensive experience with telephony or voice AI; Dograh has a community-driven documentation and a visual workflow builder to help you get started quickly.

Best inside these AI tools

Claude DesktopCursorCodex CLI

Pairs with

Claude APIStripe webhookNotion database

Why we list it on WorkflowStacks: This skill is included because it offers a flexible, open-source alternative to cloud-based voice AI platforms.

What it does

Dograh is a self-hosted voice AI platform that allows founders to automate speech tasks, such as speech-to-speech, speech-to-text, and text-to-speech, with a visual workflow builder and support for telephony and MCP

Install / run

git clone https://github.com/dograh-hq/dograh.git && cd dograh

When to use it

•When you need to automate customer service calls with a custom voice AI solution
•When you want to build a voice-activated application without relying on third-party services
•When you need to transcribe and analyze large volumes of audio data with a high degree of customization

Quick start

1Run the command `docker-compose up -d` to start the Dograh services in detached mode
2Access the visual workflow builder by navigating to `http://localhost:8080` in your web browser
3Create a new workflow by clicking the 'Create Workflow' button and selecting a template or starting from scratch
4Configure the workflow by adding nodes and connecting them to automate your desired speech task
5Test the workflow by clicking the 'Deploy' button and verifying that it works as expected

Ready-to-paste prompt

To transcribe an audio file, create a new workflow with a 'Speech-to-Text' node and configure it with the command `stt --model whisper.cpp --audio file.wav --output transcript.txt`

Heads up: Make sure you have Docker and Docker Compose installed on your system before attempting to run Dograh, as it relies on these tools to manage its services

Saves to your device