PreLing

PreLing is a command-line tool for improving language comprehension skills through gradual exposure to new vocabulary. It supports every language that spaCy supports. Because PreLing uses GPT under the hood, you must have a paid OpenAI account and an API key to run it.

Installation

Install Python 3.12 or later and pipx, then run:

pipx install preling          # install
pipx install "preling[ja]"    # alternatively: install with Japanese support
pipx upgrade preling          # upgrade
pipx uninstall preling        # uninstall (hopefully you won't need this)

Initialize a New Language

Prepare a plain-text file that contains one sentence per line in the language you want to learn. For example, you can download a monolingual corpus from OPUS. Then run:

preling init <lang> <corpus>

<lang> is the language code, and <corpus> is the path to the corpus file.

Study a Language

preling study <lang> [--audio] [--audio-only] [--model <GPT_MODEL>] \
               [--tts-model <TTS_MODEL>] [--api-key <OPENAI_KEY>] [--tts-api-key <OPENAI_OR_GCLOUD_KEY>]

• <lang> – the language code you initialized earlier.
• --audio – play audio along with the text.
• --audio-only – play audio without displaying the text.
• --tts-locale – the locale for text-to-speech (e.g., en-US, ja-JP); required for Gemini models.
• --model – the GPT model to use for grammar evaluation.
• --tts-model – the text-to-speech model to use for audio playback.
• --api-key – your OpenAI API key.
• --tts-api-key – your OpenAI API key for text-to-speech, or path to Google Cloud service account JSON file for Gemini models.

Instead of passing these options each time, you can set the environment variables PRELING_API_KEY, PRELING_MODEL, PRELING_TTS_API_KEY, and PRELING_TTS_MODEL.

View Your Progress

preling stats <lang>

Other Commands

preling path <lang>               # show the path to the language data file
preling delete <lang> [--force]   # delete the language data file; use --force to skip the confirmation prompt