Back to directory

Dograh AI

A self-hostable, open-source alternative to Vapi and Retell for building voice AI agents with a visual workflow builder, letting a team bring their own LLM, speech-to-text and text-to-speech providers.

Dograh AI

Dograh AI lets a team build production voice agents with a visual workflow builder, test them, and let AI coding assistants help design and edit them through MCP, instead of depending on a closed SaaS voice platform.

Because the source is open, every line can be modified and any LLM, TTS or STT provider can be plugged in; it supports telephony for inbound and outbound calls, including Asterisk ARI. It installs with a Docker Compose script, and collects anonymous usage data by default unless ENABLE_TELEMETRY=false is set before the startup script runs.

It is written in Python and licensed under BSD-2-Clause.

More in Speech

See all 119
  • ELI v2.0

    geteli.tech

    A private AI assistant and local runtime that runs entirely on the user's own hardware: it holds conversations by voice or text, controls the desktop, reads the screen, writes code, and builds a private model of the user over time.

  • VoiceAssistant

    github.com

    A fully local, full-duplex voice assistant for Windows that lets a user interrupt it mid-sentence and answers using visual context captured from the desktop the instant the user speaks.

  • vibe

    github.com

    A cross-platform desktop application for transcribing audio and video offline using OpenAI's Whisper models on the user's own machine, with an optional OpenAI backend when a user supplies an API key.