DICTAre™

Voice layer for AI coding agents.

Speak to your agent. No window focus required. 100% local.

dictare.io · OpenVIP™ Protocol

Why dictare

Most voice tools (Wispr Flow, Superwhisper, etc.) simulate keystrokes — they type into whatever window has focus. Switch to your browser and your code gets your voice.

Dictare uses a protocol. Your agent listens via SSE and receives transcriptions regardless of window focus. Your coding agent can be behind 3 other windows — it still gets your words.

Features

• No focus required — agent receives voice even when its window is in the background
• Agent-native — transcriptions go to the agent protocol, not a text field
• 100% local — STT runs on-device, zero data leaves your machine
• Multi-agent — switch agents by voice: "agent coding", "agent review"
• Open protocol — OpenVIP — any tool can implement the SSE endpoint
• Bidirectional — STT (voice in) + TTS (voice out)

Install

macOS + Linux — full guide

curl -fsSL https://raw.githubusercontent.com/dragfly/dictare/main/install.sh | bash

Dictare installs into ~/.local/share/dictare/versions/ and exposes a stable ~/.local/bin/dictare shim. Upgrades and rollback are managed by Dictare, not by Homebrew.

Upgrade an existing runtime:

dictare upgrade

Permissions

macOS — grant when prompted:

1. Microphone — prompted on first launch
2. Input Monitoring — System Settings → Privacy & Security → enable Dictare
3. Accessibility — needed for keyboard mode (typing into other apps)

After granting all three: dictare repair

Linux — two steps:

1. Input group (hotkey, X11 + Wayland): sudo usermod -aG input $USER — log out/in
2. ydotool (keyboard mode on Wayland): sudo apt install ydotool

Quick Start

dictare agent freddie       # starts the default profile (Claude Code)

That's it. The service starts automatically. Speak — your agent receives the transcription.

If you prefer a different coding agent:

dictare agent ozzy --profile codex      # OpenAI Codex
dictare agent gilmour --profile gemini  # Google Gemini CLI
dictare agent bowie --profile aider     # Aider

How It Works

  Microphone
      │
      ▼
  STT Module       Whisper (MLX / CTranslate2) or Parakeet (ONNX)
      │             all local, zero cold-start
      ▼
  Pipeline         submit detection, mute control, agent switching
      │
      ▼
  OpenVIP          HTTP / SSE — open protocol
      │
      ▼
  Agent            receives transcription, no window focus needed

The engine runs as a background service (launchd on macOS, systemd on Linux). STT models are preloaded at startup. Each agent connects in its own terminal.

Agent Profiles

Profiles are predefined in ~/.config/dictare/config.toml:

[agent_profiles]
default = "claude"

[agent_profiles.claude]
command = ["claude"]
description = "Claude Code"

[agent_profiles.codex]
command = ["codex"]
description = "OpenAI Codex"

[agent_profiles.pi]
command = ["pi", "--provider", "ollama", "--model", "qwen3:8b"]
continue_args = ["-c"]
description = "Pi + Ollama local, agentic with tools"

Then connect:

dictare agent freddie                      # default profile (claude)
dictare agent ozzy --profile codex         # use codex profile
dictare agent -- claude --model opus       # explicit command override

Voice Commands

Submit triggers are multilingual (en, de, es, it, fr) and fully configurable.

Hotkey Cheat Sheet

Default hotkey: Right ⌘ (macOS) / Scroll Lock (Linux).

Service Management

dictare upgrade             # Install latest runtime and switch atomically
dictare rollback            # Switch back to the previous runtime
dictare repair              # Repair runtime/service/launcher integration
dictare service install     # Install + enable (auto-starts at login)
dictare service start       # Start the service
dictare service stop        # Stop the service
dictare service restart     # Restart the service
dictare service status      # Show service and engine status
dictare service logs        # View recent logs
dictare service uninstall   # Remove the service

Keyboard Mode

No agent? Use dictare as a dictation tool — voice to keystrokes in any app.

dictare config set output.mode keyboard

Hotkey to toggle listening (configurable):

• macOS: Right ⌘ by default
• Linux: Scroll Lock by default

dictare config set hotkey.key KEY_RIGHTALT   # change hotkey

Text-to-Speech

dictare speak "Hello world"
dictare speak --engine piper "Hello"
echo "Hello" | dictare speak

Engines: espeak, say (macOS), piper, kokoro

Configuration

dictare config edit           # Open config in editor
dictare config list           # Show all settings
dictare config get stt.model
dictare config set stt.language it

Full configuration reference at dictare.io/docs/configuration.

Development

git clone https://github.com/dragfly/dictare && cd dictare

# macOS Apple Silicon (MLX GPU acceleration)
uv sync --python 3.11 --extra mlx

# macOS Intel / Linux
uv sync --python 3.11

# Run engine in foreground
uv run --python 3.11 dictare serve

# Tests
uv run --python 3.11 pytest tests/ -x

# Tests (parallel)
uv run --python 3.11 pytest tests/ -x -n auto

Ghostty users: add keybind = shift+enter=text:\n to config. See TERMINAL_COMPATIBILITY.md.

Protocol

dictare is the reference implementation of OpenVIP — an open protocol for voice input to AI agents. Any tool can implement the SSE endpoint and receive voice transcriptions from dictare.

Legacy Homebrew installs

If you installed Dictare with Homebrew, remove the legacy install first:

curl -fsSL https://raw.githubusercontent.com/dragfly/dictare/main/scripts/uninstall.sh | bash

Then reinstall with the new installer:

curl -fsSL https://raw.githubusercontent.com/dragfly/dictare/main/install.sh | bash

Your config and models are preserved in ~/.config/dictare/ and ~/.local/share/dictare/.

License

MIT