Metadata-Version: 2.4
Name: vupai
Version: 0.9.0
Summary: Voice UI for AI panes - push-to-talk voice control over tmux agent panes
Project-URL: Homepage, https://github.com/itsjrsa/vupai
Project-URL: Repository, https://github.com/itsjrsa/vupai
Project-URL: Issues, https://github.com/itsjrsa/vupai/issues
Author-email: José Andrade <jrsa2012@gmail.com>
License-Expression: MIT
License-File: LICENSE
Keywords: ai-agents,apple-silicon,macos,mlx,parakeet,push-to-talk,speech-to-text,tmux,voice
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Environment :: MacOS X
Classifier: Intended Audience :: Developers
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Classifier: Topic :: Terminals
Classifier: Topic :: Utilities
Requires-Python: >=3.11
Requires-Dist: metaphone
Requires-Dist: parakeet-mlx; sys_platform == 'darwin' and platform_machine == 'arm64'
Requires-Dist: pynput
Requires-Dist: rapidfuzz
Description-Content-Type: text/markdown

<p align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="./assets/brand/vupai-lockup-dark.png">
    <img alt="vupai" src="./assets/brand/vupai-lockup.png" width="260">
  </picture>
</p>

<p align="center">
  <strong>Voice UI for AI panes</strong>: push-to-talk voice control for your tmux agent panes, on macOS, with on-device speech.
</p>

<p align="center">
  <a href="https://github.com/itsjrsa/vupai/actions/workflows/ci.yml"><img alt="CI" src="https://img.shields.io/github/actions/workflow/status/itsjrsa/vupai/ci.yml?branch=master&label=CI"></a>
  <a href="https://pypi.org/project/vupai/"><img alt="PyPI" src="https://img.shields.io/pypi/v/vupai.svg?v=0.9.0"></a>
  <a href="https://pypi.org/project/vupai/"><img alt="Downloads" src="https://img.shields.io/pypi/dm/vupai.svg"></a>
  <a href="./LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-blue.svg"></a>
  <a href="https://www.python.org/"><img alt="Python" src="https://img.shields.io/badge/python-%3E%3D3.11-brightgreen.svg"></a>
  <img alt="Platform" src="https://img.shields.io/badge/platform-macOS%20Apple%20Silicon-black.svg">
  <a href="https://github.com/astral-sh/ruff"><img alt="Ruff" src="https://img.shields.io/badge/lint-ruff-261230.svg"></a>
</p>

*vupai* (say "voo-pie") is a **V**oice **U**I for your AI **pa**nes.

Hold a key, speak, and what you say is typed into the right tmux pane: the one
you're looking at, or an agent you call by name (*"atlas, run the tests"*).
Speech-to-text runs on-device with NVIDIA Parakeet (via Apple MLX): no cloud,
no API keys.

Built for a tmux-centric workflow where you keep several coding agents and
shells open at once and want to drive them by voice without reaching for the
mouse. New panes launch an agent by default (`claude` out of the box) and should
work with other agentic coding tools (Codex, Gemini, …), though testing so far
has focused on Claude Code.

**📚 Full documentation: [itsjrsa.github.io/vupai](https://itsjrsa.github.io/vupai/)** ·
🎬 [demo clips](https://itsjrsa.github.io/vupai/voice-commands/#see-it-in-action)

## Install

vupai is **macOS Apple-Silicon only** (it depends on Apple MLX for on-device
speech). It needs `tmux`, `sox`, and [`uv`](https://docs.astral.sh/uv/):

```bash
brew install tmux sox uv
uv tool install vupai
vupai setup        # one-time bootstrap: mic, hotkeys, model download, macOS permissions
```

The Parakeet model (~2 GB) downloads automatically on first use. Full details
(requirements, from-source install, permissions) are in the
[install](https://itsjrsa.github.io/vupai/install/) and
[setup](https://itsjrsa.github.io/vupai/setup/) docs.

## Quickstart

```bash
vupai              # attach-or-create the session named after the cwd
```

Then hold a push-to-talk key and speak:

- **Right-Option** (dictation): what you say is typed into the focused pane.
  Start with a pane's name (*"atlas, run the tests"*) to address it anywhere.
- **Right-Command** (system): voice commands that act on the panes instead of
  typing: *"create 3 panes"*, *"focus atlas"*, *"board"*, *"note: fix the retry
  logic"*, *"everyone, pull main"*.

It's still tmux: every normal binding keeps working, and vupai runs on its own
tmux server so your existing setup is untouched.

## Learn more

The [documentation site](https://itsjrsa.github.io/vupai/) covers everything:

- [Usage](https://itsjrsa.github.io/vupai/usage/) · [Voice commands](https://itsjrsa.github.io/vupai/voice-commands/) · [Silent mode (no mic)](https://itsjrsa.github.io/vupai/silent-mode/)
- Multi-agent supervision: [board](https://itsjrsa.github.io/vupai/board/) · [activity ledger](https://itsjrsa.github.io/vupai/activity-ledger/) · [review](https://itsjrsa.github.io/vupai/review/) · [task pile](https://itsjrsa.github.io/vupai/tasks/) · [squad](https://itsjrsa.github.io/vupai/squad/)
- Reference: [configuration](https://itsjrsa.github.io/vupai/configuration/) · [SSH hosts](https://itsjrsa.github.io/vupai/remote-hosts/) · [tmux tips](https://itsjrsa.github.io/vupai/tmux-tips/) · [uninstall](https://itsjrsa.github.io/vupai/uninstall/) · [roadmap](https://itsjrsa.github.io/vupai/roadmap/)

Contributing? See [AGENTS.md](AGENTS.md). Ideas and PRs are welcome:
[open an issue](https://github.com/itsjrsa/vupai/issues).

## License

[MIT](LICENSE). (Note: `pynput` is LGPL-3.0 and the Parakeet model weights are
CC-BY-4.0; both are runtime dependencies, not part of this repo's code.)
