deepl-cli

Translate text using the DeepL API via the deepl-cli command-line tool. Use when the user asks to: translate text, translate to another language, use DeepL, translate with formality control, or pipe text through a translation. Supports all DeepL language pairs, source language auto-detection, context-aware translation, and formality levels (formal/informal).

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "deepl-cli" with this command: npx skills add daliusd/deepl-cli/daliusd-deepl-cli-deepl-cli

deepl-cli

CLI tool for translating text using the DeepL API. Pipe-friendly, supports context and formality options.

Prerequisites

Installation

npm install -g @daliusd/deepl-cli

Configuration

Create ~/.config/deepl-cli/config.json:

mkdir -p ~/.config/deepl-cli

Option A -- Static API key:

{
  "api_key": "your-deepl-api-key"
}

Option B -- Command-based key (for password managers like pass, 1Password CLI, etc.):

{
  "api_key_command": "pass show deepl-api-key"
}

If both are present, api_key_command takes precedence.

Commands

All translation is done via a single command:

deepl-cli [options] [text]

Basic Translation

deepl-cli -t de "Hello, world!"

Specify Source Language

deepl-cli -t de -s en "Hello"

By default the source language is auto-detected. Use -s only when auto-detection is insufficient.

Context-Aware Translation

Context influences the translation but is not itself translated or billed:

deepl-cli -t de -c "This is a greeting in a formal business email" "Hello"

Formality Control

# Formal
deepl-cli -t de -f more "How are you?"

# Informal
deepl-cli -t de -f less "How are you?"

Valid formality values: less, more, default, prefer_less, prefer_more.

Piped Input

echo "Hello, world!" | deepl-cli -t de

Translated text goes to stdout with no extra formatting, making it pipeline-friendly:

echo "Hello" | deepl-cli -t de | pbcopy

Verbose Mode

Metadata is written to stderr so stdout remains clean:

deepl-cli -t de -v "Hello, world!"
# stdout: Hallo, Welt!
# stderr: Detected source language: en
# stderr: Billed characters: 13

Options Reference

OptionShortDescription
--target <lang>-tTarget language code (required, e.g. de, en-US, fr)
--source <lang>-sSource language code (default: auto-detect)
--context <text>-cAdditional context for translation (not translated, not billed)
--formality <level>-fFormality: less, more, default, prefer_less, prefer_more
--verbose-vShow metadata (detected source language, billed characters)
--help-hShow help
--versionShow version

Common Language Codes

Language codes are case-insensitive and follow ISO 639-1.

Source languages (or omit for auto-detection):

CodeLanguage
enEnglish
deGerman
frFrench
esSpanish
itItalian
jaJapanese
zhChinese
plPolish
nlDutch
ptPortuguese
ruRussian

Target languages (some include regional variants):

CodeLanguage
en-USEnglish (American)
en-GBEnglish (British)
deGerman
frFrench
esSpanish
itItalian
jaJapanese
zh-HansChinese (Simplified)
zh-HantChinese (Traditional)
plPolish
nlDutch
pt-BRPortuguese (Brazilian)
pt-PTPortuguese (European)
ruRussian

See the DeepL API documentation for the full list.

Tips

  • No arguments or --help shows usage information.
  • Multiple words as positional arguments are joined with a space: deepl-cli -t de Hello world translates "Hello world".
  • Verbose mode writes metadata to stderr, so piping stdout is always safe.
  • api_key_command is recommended over api_key to avoid storing secrets in plain text.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

Ai Freelancing Guide

Provides a complete guide to AI freelancing including niche analysis, pricing, client acquisition, proposal templates, and delivery workflows.

Registry SourceRecently Updated
Coding

Ai Code Assistant

提供多语言AI智能代码处理与批量自动化,显著提升开发效率,适合企业、团队及自由职业者。

Registry SourceRecently Updated
Coding

Life Control

Orchestrate the Life Control CLI skill for OpenClaw agent fleets: initialize the Life Control database, register agent personas, wire Telegram bots, and run daily routines (Morning Alignment, Body Protocol, Financial Pulse, Social Radar, Work Priming, Shutdown). Use when a user asks to create or run a Life Control system, OpenClaw skill integration, or agent persona automation for personal life tracking.

Registry SourceRecently Updated