GUIDE

Mac text to speech: natural offline voices on macOS

macOS has a built-in say command and system voices, handy for a quick check. When you need character voices, a voice of your own or the same voice in 31 languages saved as audio files, the free SuperClonica engine brings the neural model Supertonic 3 to your Mac. It runs offline on the processor, with no graphics card.

This guide shows how to install it in a virtual environment, voice text from the Terminal, read the clipboard aloud with a keyboard shortcut and choose voices.

Browse voices Install the SuperClonica engine

What you need

The GPU package of the engine is for NVIDIA cards only, so on a Mac use superclonica-cpu.

  • A Mac with Apple Silicon and Python 3.10 or newer, from python.org or Homebrew.
  • About 400 MB of disk space for the Supertonic 3 model, downloaded once.
  • The processor is enough: the engine needs no graphics card.
  • A voice: the ten built-in voices M1 to M5 and F1 to F5, or a JSON file from the catalog.

Install in a virtual environment

Open the Terminal and install the engine into its own environment: python3 -m venv ~/.venvs/tts && ~/.venvs/tts/bin/python -m pip install superclonica-cpu. The command is then ~/.venvs/tts/bin/superclonica; add the folder to your PATH or create an alias in ~/.zshrc.

Voice text from the Terminal

The model downloads on the first run; after that the engine works without the internet.

  • One phrase: superclonica --text "Hello from my Mac." --voice F1 --lang en --output hello.wav && afplay hello.wav.
  • A whole file: --text-file article.txt instead of --text; long texts are split at natural pauses and joined into one WAV.
  • Change --lang for other languages, for example de, es or ja.
  • Limit the processor threads with --threads 4 if you keep working while it runs.

Read the clipboard with a shortcut

In the Shortcuts app, create a shortcut with a Run Shell Script action containing: pbpaste > /tmp/clip.txt && ~/.venvs/tts/bin/superclonica --text-file /tmp/clip.txt --voice F1 --lang en --output /tmp/clip.wav && afplay /tmp/clip.wav. Give it a keyboard shortcut. Copy any text, press the keys, and the engine reads it aloud in the chosen voice.

Voices and your own voice

Every voice in the SuperClonica catalog has a page where you can voice a phrase of 30 to 100 characters for free online. Free voices download without an account; paid ones are bought once and stay yours as a JSON file. Training your own voice in the studio needs a Windows PC with an NVIDIA graphics card; from a Mac you can order a voice on the exchange from an author who trains it, then use it here offline.