Deploy Now

SaaS Alternative

Vapi Retell Bland AI

Categories

Self-Hosted AI Automation Communication Voice AI Customer Service Telephony

Stars

5,618

Forks

1,386

Watchers

46

Developer links

Last Updated: 09-09-2026
Share on X

Dograh

Build a voice AI agent that answers calls, qualifies leads, books appointments, and transfers to a human when needed, all from a drag-and-drop workflow builder in your browser. Dograh ships as a Docker Compose stack (API, web UI, Postgres, Redis, MinIO) that you self-host on any Linux server with automatic HTTPS provisioning via Let's Encrypt. The visual workflow builder lets you design multi-turn conversation flows by connecting nodes for greetings, intent classification, tool calls, and handoffs; describe your use case in plain English and the platform generates the LLM prompt and node graph for you. Connect your own speech-to-text, LLM, and text-to-speech providers (OpenAI, Anthropic, Gemini, ElevenLabs, Deepgram, local Whisper, Kokoro, or any OpenAI-compatible endpoint) or use the built-in Speech-to-Speech mode with Gemini Flash Live and GPT-Realtime-2 for sub-200ms latency. Telephony plugs in through Twilio, Vonage, Vobiz, or Cloudonix for inbound and outbound calling, with live agent transfer when the conversation needs a human. Webhook tool calls connect to Salesforce, HubSpot, Google Calendar, Cal.com, or any REST API without writing orchestration code. The ClonedVoice feature mixes real human voice recordings for high-frequency phrases with neural TTS fallback for dynamic content, cutting costs while improving caller trust. A built-in MCP server lets AI coding agents like Claude Code or Cursor design, test, and edit workflows through natural language. Deploy on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD 2-Clause licensed.

Dograh
Dograh
Dograh
Dograh
Dograh
Dograh
Dograh

Benefits

  • No Vendor Lock-in on Voice AI
  • Self-host the entire platform on your own server with full source access under BSD 2-Clause. Your call recordings, transcripts, and conversation data never leave your infrastructure.
  • Visual Workflow Builder
  • Design multi-turn voice agent conversations by connecting nodes in a drag-and-drop canvas. Describe your use case in English and the platform generates the prompt and flow automatically.
  • Bring Any Provider
  • Connect your own LLM, speech-to-text, and text-to-speech keys from 30+ providers, or run locally with Whisper, Llama, and Kokoro for zero per-minute cost and complete data residency.
  • Production Telephony Built In
  • Twilio, Vonage, Vobiz, and Cloudonix integrations handle inbound and outbound calls. Live agent transfer routes the conversation to a human when the AI reaches its limits.

Features

  • Speech-to-Speech Mode
  • Sub-200ms latency via Gemini Flash Live and GPT-Realtime-2. Bypasses the traditional STT-LLM-TTS pipeline for natural, low-delay voice conversations.
  • ClonedVoice Mixing
  • Record real human voice clips for greetings and transitions, then fall back to neural TTS for dynamic content. Reduces cost and improves outbound conversion rates.
  • Webhook Tool Calls
  • Connect to Salesforce, HubSpot, Google Calendar, Cal.com, or any REST API via webhook nodes. The agent books appointments, updates CRM records, and triggers workflows mid-call.
  • MCP Server
  • A built-in Model Context Protocol server lets AI coding agents design, test, and deploy voice workflows through natural language conversation instead of manual UI clicks.
  • Call Monitoring
  • Real-time call transcripts, sentiment analysis, and QA scoring. Review recordings, flag issues, and iterate on agent performance from the dashboard.