automation

dograh: Automate Voice AI

Self-hosted voice AI platform. Automate speech tasks with ease.
intermediateโฑ 30 minutes๐Ÿ’ต Free + LLM API costs
5,459 stars1,325 forksPythonGuide quality 8/10Updated 8/22/2026100% free ยท 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
  • โ€ขWhen you need to automate customer service calls with a custom voice AI solution
  • โ€ขWhen you want to build a voice-activated application without relying on third-party services
  • โ€ขWhen 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 โ€” one click puts this in Claude, Cursor, Antigravity and more.

๐Ÿ› ๏ธ Technical setup

Expect 20โ€“40 minutes in a terminal โ€” or let your AI agent drive it.

Try it instantly โ€” 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 โ€” 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 (~179k lines across 971 code files, plus 226 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
~179k lines ยท 971 code files ยท days to read โ€” 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 62%TypeScript 34%Shell 2%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here โ€” 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 โ€” copy this to get going
What's in each folder
api/Backend / API771 files
ui/Frontend / UI379 files
docs/Documentation198 files
examples/Examples you can copy13 files
evals/Evaluations & benchmarks58 files
sdk/SDKs / client libraries53 files
deploy/Deployment / infrastructure45 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? Claim your listing โ†’ and earn 85% of every sale.