workflowstacks
automation

dograh: Automate Voice AI

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

From the repo · “Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.”

intermediate⏱ 30 minutes💵 Free + LLM API costs
5,923 stars+54★ this week1,511 forksPythonGuide quality 8/10 · reviewed Jun 6Updated 10/20/2026100% free · open source
What it is

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

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."

Best insideClaude DesktopCursorCodex CLI
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
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
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/dograh && curl -fsSL https://workflowstacks.com/api/skills/dograh/claude-skill -o ~/.claude/skills/dograh/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How dograh: Automate Voice AI works
Codeflow
Free to inspect

Dograh: Automate Voice AI is a very large Python project (~187k lines across 1002 code files, plus 254 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, BSD-2-Clause license, has a test suite.

Size
Very large codebase
~187k lines · 1002 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Docker
No API keys detected
Python 64%TypeScript 32%Shell 2%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    api/app.py
    Where the program starts running
  4. 4
    examples/README.md
    A worked example — copy this to get going
What's in each folder
api/Backend / API824 files
ui/Frontend / UI386 files
docs/Documentation199 files
examples/Examples you can copy13 files
evals/Evaluations & benchmarks58 files
sdk/SDKs / client libraries53 files
deploy/Deployment / infrastructure51 files
scripts/Helper scripts44 files
READMEHas testsDocumentedCI checksDocker readyExamples includedBSD-2-Clause licenseUpdated this month
Quick Actions
Details
Creator
dograh-hq
Language
Python
Category
automation
Published
9/9/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/dograh.svg)](https://workflowstacks.com/skills/dograh?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Automate your meeting summaries

A private form takes any transcript (from Zoom, Meet, Otter, Fireflies) and emails you back a structured summary: a TL;DR, the decisions made, and action items with owners.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Outcome guide

Turn meeting notes into a summary email automatically

Paste the transcript into a private form and the workflow writes and emails a concise recap — decisions, owners, open questions — that people will actually read.

Related skills

More automation tools founders pair with this one.

automation★ 208,277
n8n: Scale Your Startup with 207k+ GitHub-Star Automation
n8n lets founders automate workflows across 400+ services, blending visual no‑code design with custom TypeScript code—self‑hosted or cloud.
automation★ 155,897
Langflow: Rapidly Build AI Agents & Workflows
Create and launch AI‑powered agents and multi‑step workflows without deep ML code—ideal for founders scaling generative‑AI products. 155k+ GitHub stars
automation★ 133,722
MoneyPrinterTurbo: AI Video Automation
Generate short videos with one click using AI. For founders needing automation.
automation★ 18,047
rowboat: AI coworker that remembers your workflow
Boost founder productivity with rowboat’s open‑source AI agent that retains context across tasks. Ideal for startups seeking seamless automation, backed by 18k+ GitHub stars.
automation★ 233
Universal-Intel-Chipset-Updater
Security-focused tool for automatic Intel chipset INF detection and installation. SHA-256 verified, Intel Authenticode validated, System Restore Point
automation★ 613
terraform-provider-databricks
Databricks Terraform Provider