#3030th of 67 in VoiceFor voice, speech and music
dograh
Visual builder for voice agents with telephony, a Vapi and Retell alternative
- Stars
- 6k
- License
- BSD-2-Clause
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
296 on 3 Apr 20266,004 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Dograh is a self-hostable platform for building inbound and outbound voice agents in a visual workflow editor, with a browser Test Audio and Test Chat panel. It integrates telephony providers such as Twilio, Vonage, Telnyx, Plivo and Asterisk ARI, and accepts your own LLM, TTS and STT providers. It also ships an MCP server so coding agents can create and edit workflows.
Who it is for: Teams self-hosting voice agents for phone calls instead of using Vapi or Retell
Strengths
- Built-in telephony: Twilio, Vonage, Telnyx, Plivo, Vobiz, Cloudonix, Asterisk ARI
- Bring your own LLM, TTS, STT, or use the bundled stack with no keys
- MCP server lets coding agents create and edit workflows
- Python and Node SDKs for agent creation and outbound calls
Weaknesses
- Quickstart opens a public trycloudflare.com tunnel by default
- Anonymous telemetry is on by default; opt out via ENABLE_TELEMETRY=false
- Signup is enabled by default and must be closed through .env
What it needs
- Compose
- Needs Docker Compose, MinIO or S3-compatible storage, Telephony provider (optional)
- Models: Any LLM, TTS and STT provider, Bundled Dograh LLM/TTS/STT stack
- port 3010
Quick answers
Is dograh open source?
Yes. Its code is on GitHub under the BSD-2-Clause license.
Can you run dograh with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Voice
See all 67| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 97 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 89 out of 100 |
| 3 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 89 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 82 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 81 out of 100 |