Bard

Bard is a text-to-speech client that integrates on the desktop.

• Multiple input sources. Feed bard plain text, the clipboard, a URL, an HTML file, or a PDF — it extracts the readable content (with readability) and speaks it. Useful for reading paywalled articles via "View Page Source".
• Four TTS backends. OpenAI and ElevenLabs (remote, API key) plus Kokoro and Piper (local, free, offline, multilingual). Switch backend, model, and voice at runtime from the tray menu without restarting.
• Desktop player. A system-tray icon with playback controls, or a keyboard-driven terminal dashboard with --no-tray. A global shortcut can read the clipboard from anywhere (works on Wayland too).
• Batch or interactive. Pass -o file.mp3 to synthesise straight to an audio file and exit, or run interactively and drive playback from the tray.

📖 Documentation

Full documentation lives at https://perrette.github.io/bard/:

• Installation (incl. system dependencies)
• Quickstart
• Backends & voices
• Tray menu
• Guides: input sources, batch render, global keyboard shortcut, fine-tuning, player, Android

Install

Install the system dependencies, then the app with all optional backends:

sudo apt-get install portaudio19-dev xclip #  portaudio19-dev becomes portaudio with Homebrew
sudo apt install libcairo-dev libgirepository1.0-dev gir1.2-appindicator3-0.1  # Ubuntu ONLY (not needed on MacOS)
pip install PyGObject # Ubuntu ONLY (not needed on MacOS)

pip install bard-cli[all]          # OpenAI, ElevenLabs, Kokoro (no Piper)
pip install bard-cli[all-local]    # all of the above + Piper

See the installation page for individual backend extras and the GNOME launcher.

Quickstart

bard

defaults to bard --backend openai --voice alloy --model gpt-4o-mini-tts (assuming OPENAI_API_KEY is set). An icon shows up in the system tray with an option to read the clipboard aloud.

You can also do a one-off reading:

bard --text "Hello world, how are you today"
bard --clipboard
bard --url "example.com"
bard --pdf-file /path/to/document.pdf

See the quickstart and input sources pages for more.

From the same author

A few other open-source tools I maintain.

Scientific writing & data

• texmark — write scientific articles in Markdown and convert them to journal-ready LaTeX/PDF.
• papers — command-line BibTeX bibliography and PDF library manager.
• datamanifest — declarative, reproducible dataset management. (See also the datamanifest.toml format spec and the DataManifest.jl Julia port.)

Speech to Text (dictate) and Text to Speech (read-aloud) tools

• scribe — speech-to-text dictation.

Acknowledgements

The player was devised in conversation with Mistral's Le Chat and OpenAI's ChatGPT, and my own experience with pystray on scribe.