Language Learning

# Basic usage
labelingo screenshot.png

# Translate to a specific language (e.g., French)
labelingo screenshot.png -l fr

# Process multiple files
labelingo *.png -o translated/

# Install with additional OCR support
pip install 'labelingo[ocr]'

# Basic usage (uses Google Translate TTS by default)
add2anki 'Hello, how are you?'

# Start interactive mode
add2anki

# Specify a deck
add2anki --deck 'Chinese Vocabulary' 'u4f60u597d'

# Use ElevenLabs for high-quality audio
add2anki --tts-provider elevenlabs 'Bonjour, comment allez-vous?'

# Process an audio file with default settings
audio2anki input.mp3

# Specify source and target languages
audio2anki input.mp3 --source-language japanese --target-language english

# Process with voice isolation (uses ElevenLabs API)
audio2anki --voice-isolation input.m4a

# Configure settings
audio2anki config set use_cache true

# Create a video with subtitles from an audio file and subtitle file
subburn audio.mp3 subtitles.srt

# Automatic transcription using OpenAI Whisper
subburn audio.mp3

# Create a video with a still image background
subburn input.mp3 subtitles.srt background.jpg

# Add subtitles to an existing video
subburn video.mp4 subtitles.srt

# Specify custom output path
subburn input.mp3 subtitles.srt -o output.mov

# Import the package
from speech_provider import get_voice_provider

# Basic usage
provider = get_voice_provider()

# Get available voices for a specific language
voices = provider.get_voices(lang='en-US')

if voices:
    # Create and play an utterance with the first available voice
    utterance = voices[0].create_utterance('Hello, welcome to my application!')

    # Start speaking
    utterance.play()

# Use with Eleven Labs for higher quality voices
elevenlabs_provider = get_voice_provider(
    elevenlab_api_key='your-api-key',
    cache_max_age=3600  # Cache for 1 hour
)

# Get default voice for a language
default_voice = elevenlabs_provider.get_default_voice(lang='zh-CN')

if default_voice:
    utterance = default_voice.create_utterance('你好，欢迎使用我的应用程序！')
    utterance.play()

# Get voices for specific language
voices = provider.get_voices(lang='fr-FR')
for voice in voices:
    print(f"Voice: {voice.name}, Language: {voice.lang}")

# Basic usage with context-awareness
from contextual_langdetect import contextual_detect

# Example multilingual text
sentences = [
    "你好。",                           # Chinese
    "你好吗?",                          # Chinese
    "很好。",                           # Could be detected as Japanese without context
    "我家也有四个,刚好。",                # Chinese
    "那么现在天气很冷,你要开暖气吗?",      # Chinese (Wu dialect)
    "Okay, fine I'll see you next week.", # English
    "Great, I'll see you then."          # English
]

# Context-aware detection (default)
languages = contextual_detect(sentences)
print(languages)  # ['zh', 'zh', 'zh', 'zh', 'zh', 'en', 'en']

# Context-unaware detection
languages = contextual_detect(sentences, context_correction=False)
print(languages)  # ['zh', 'zh', 'ja', 'zh', 'wuu', 'en', 'en']

# Get language distribution in a document
from contextual_langdetect.detection import count_by_language

mixed_sentences = [
    "Hello world.",        # English
    "Bonjour le monde.",   # French
    "Hallo Welt.",         # German
    "Hello again."         # English
]

counts = count_by_language(mixed_sentences)
print(counts)  # {'en': 2, 'fr': 1, 'de': 1}

# Get the majority language in a document
from contextual_langdetect.detection import get_majority_language

majority = get_majority_language(mixed_sentences)
print(majority)  # 'en'