ttsforge 0.1.0__py3-none-any.whl

ttsforge/cli/helpers.py

@@ -0,0 +1,76 @@
+"""Shared utilities and helpers for CLI commands."""
+
+from rich.console import Console
+
+# Shared console instance for all CLI commands
+console = Console()
+
+
+def parse_voice_parameter(voice: str) -> tuple[str | None, str | None]:
+    """Parse voice parameter to detect if it's a single voice or a blend.
+
+    Args:
+        voice: Voice parameter (e.g., 'af_sky' or 'af_nicole:50,am_michael:50')
+
+    Returns:
+        Tuple of (voice, voice_blend) where one will be None
+
+    Examples:
+        >>> parse_voice_parameter('af_sky')
+        ('af_sky', None)
+        >>> parse_voice_parameter('af_nicole:50,am_michael:50')
+        (None, 'af_nicole:50,am_michael:50')
+    """
+    # Detect if it's a blend (contains both : and ,)
+    if ":" in voice and "," in voice:
+        return (None, voice)
+    else:
+        return (voice, None)
+
+
+def get_version() -> str:
+    """Get the package version."""
+    try:
+        from .._version import version
+
+        return version
+    except ImportError:
+        return "0.0.0+unknown"
+
+
+# Default sample text for testing TTS settings
+DEFAULT_SAMPLE_TEXT = (
+    "The quick brown fox jumps over the lazy dog. "
+    "This sample text demonstrates the text-to-speech capabilities, "
+    "including punctuation handling, and natural speech flow."
+)
+
+
+# Demo sample text per language
+DEMO_TEXT = {
+    "a": "Hello! This audio was generated by {voice}. How do you like it?",
+    "b": "Hello! This audio was generated by {voice}. How do you like it?",
+    "e": "Hola! Este audio fue generado por {voice}. Que te parece?",
+    "f": "Bonjour! Cet audio a ete genere par {voice}. Comment le trouvez-vous?",
+    "h": "Namaste! Yah audio {voice} dwara banaya gaya hai. Aapko kaisa laga?",
+    "i": "Ciao! Questo audio e stato generato da {voice}. Ti piace?",
+    "j": "Konnichiwa! Kono onsei wa {voice} ni yotte sakusei saremashita.",
+    "p": "Ola! Este audio foi gerado por {voice}. O que voce achou?",
+    "z": "Ni hao! Zhe ge yinpin shi you {voice} shengcheng de.",
+}
+
+# Preset voice blends for demo command
+# Format: (blend_string, description)
+VOICE_BLEND_PRESETS = [
+    # Same language, different gender
+    ("af_nicole:50,am_michael:50", "American female + male blend"),
+    ("bf_emma:50,bm_george:50", "British female + male blend"),
+    # Same gender, different accent
+    ("af_heart:50,bf_emma:50", "American + British female blend"),
+    ("am_adam:50,bm_daniel:50", "American + British male blend"),
+    # Same gender, different voice
+    ("af_nicole:50,af_bella:50", "Two American females blend"),
+    ("am_adam:50,am_eric:50", "Two American males blend"),
+    # Multi-voice blend
+    ("af_heart:33,af_nicole:33,af_bella:34", "Three American females blend"),
+]

ttsforge/constants.py

@@ -0,0 +1,164 @@
+"""Constants for ttsforge - voices, languages, and formats."""
+
+# from pykokoro.onnx_backend import VOICE_NAMES_V1_0
+# from pykokoro.onnx_backend import VOICE_NAMES_V1_1_ZH, VOICE_NAMES_V1_1_DE
+
+from pykokoro.onnx_backend import VOICE_NAMES_V1_0 as VOICE_NAMES
+
+# Re-export from pykokoro for convenience
+VOICES = VOICE_NAMES
+
+# Audio constants from pykokoro
+try:
+    from pykokoro.constants import SAMPLE_RATE as _SAMPLE_RATE
+
+    SAMPLE_RATE: int = int(_SAMPLE_RATE)
+except ImportError:
+    SAMPLE_RATE = 24000  # Fallback value
+
+# Program Information
+PROGRAM_NAME = "ttsforge"
+PROGRAM_DESCRIPTION = "Generate audiobooks from EPUB files using Kokoro ONNX TTS."
+
+# Language code to description mapping
+LANGUAGE_DESCRIPTIONS = {
+    "a": "American English",
+    "b": "British English",
+    "e": "Spanish",
+    "f": "French",
+    "h": "Hindi",
+    "i": "Italian",
+    "j": "Japanese",
+    "p": "Brazilian Portuguese",
+    "z": "Mandarin Chinese",
+}
+
+# ISO language code to ttsforge language code mapping
+ISO_TO_LANG_CODE = {
+    "en": "a",  # Default to American English
+    "en-us": "a",
+    "en-gb": "b",
+    "en-au": "b",
+    "es": "e",
+    "es-es": "e",
+    "es-mx": "e",
+    "fr": "f",
+    "fr-fr": "f",
+    "fr-ca": "f",
+    "hi": "h",
+    "it": "i",
+    "ja": "j",
+    "pt": "p",
+    "pt-br": "p",
+    "pt-pt": "p",
+    "zh": "z",
+    "zh-cn": "z",
+    "zh-tw": "z",
+}
+
+# Voice prefix to language code mapping
+VOICE_PREFIX_TO_LANG = {
+    "af": "a",  # American Female
+    "am": "a",  # American Male
+    "bf": "b",  # British Female
+    "bm": "b",  # British Male
+    "ef": "e",  # Spanish Female
+    "em": "e",  # Spanish Male
+    "ff": "f",  # French Female
+    "fm": "f",  # French Male
+    "hf": "h",  # Hindi Female
+    "hm": "h",  # Hindi Male
+    "if": "i",  # Italian Female
+    "im": "i",  # Italian Male
+    "jf": "j",  # Japanese Female
+    "jm": "j",  # Japanese Male
+    "pf": "p",  # Portuguese Female
+    "pm": "p",  # Portuguese Male
+    "zf": "z",  # Chinese Female
+    "zm": "z",  # Chinese Male
+}
+
+# Language code to default voice mapping
+DEFAULT_VOICE_FOR_LANG = {
+    "a": "af_heart",
+    "b": "bf_emma",
+    "e": "ef_dora",
+    "f": "ff_siwis",
+    "h": "hf_alpha",
+    "i": "if_sara",
+    "j": "jf_alpha",
+    "p": "pf_dora",
+    "z": "zf_xiaoxiao",
+}
+
+# Supported output audio formats
+SUPPORTED_OUTPUT_FORMATS = [
+    "wav",
+    "mp3",
+    "flac",
+    "opus",
+    "m4b",
+]
+
+# Formats that require ffmpeg
+FFMPEG_FORMATS = ["m4b", "opus"]
+
+# Formats supported by soundfile directly
+SOUNDFILE_FORMATS = ["wav", "mp3", "flac"]
+
+# Default configuration values
+DEFAULT_CONFIG = {
+    "default_voice": "af_heart",
+    "default_language": "a",
+    "default_speed": 1.0,
+    "default_format": "m4b",
+    "use_gpu": False,  # GPU requires onnxruntime-gpu
+    # Model quality: fp32, fp16, q8, q8f16, q4, q4f16, uint8, uint8f16
+    "model_quality": "fp32",
+    "model_variant": "v1.0",
+    "silence_between_chapters": 2.0,
+    "save_chapters_separately": False,
+    "merge_at_end": True,
+    "auto_detect_language": True,
+    "default_split_mode": "auto",
+    "default_content_mode": "chapters",  # Content mode for read: chapters or pages
+    "default_page_size": 2000,  # Synthetic page size in characters for pages mode
+    "pause_clause": 0.5,
+    "pause_sentence": 0.7,
+    "pause_paragraph": 0.9,
+    "pause_variance": 0.05,
+    "pause_mode": "auto",  # "tts", "manual", or "auto
+    # Language override for phonemization (e.g., 'de', 'fr', 'en-us')
+    # If None, language is determined from voice prefix
+    "phonemization_lang": None,
+    # Chapter announcement settings
+    "announce_chapters": True,  # Read chapter titles aloud before content
+    "chapter_pause_after_title": 2.0,  # Pause after chapter title (seconds)
+    "output_filename_template": "{book_title}",
+    "chapter_filename_template": "{chapter_num:03d}_{book_title}_{chapter_title}",
+    "phoneme_export_template": "{book_title}",
+    # Fallback title when metadata is missing
+    "default_title": "Untitled",
+    # Mixed-language phonemization settings (disabled by default)
+    "use_mixed_language": False,  # Enable automatic language detection
+    "mixed_language_primary": None,  # Primary language (None = use current lang)
+    "mixed_language_allowed": None,  # List of allowed languages (required if enabled)
+    "mixed_language_confidence": 0.7,  # Detection confidence threshold (0.0-1.0)
+}
+
+# Audio settings
+# SAMPLE_RATE is imported from pykokoro at top of file
+AUDIO_CHANNELS = 1
+
+# Sample texts for voice preview (per language)
+SAMPLE_TEXTS = {
+    "a": "This is a sample of the selected voice.",
+    "b": "This is a sample of the selected voice.",
+    "e": "Este es una muestra de la voz seleccionada.",
+    "f": "Ceci est un exemple de la voix sélectionnée.",
+    "h": "यह चयनित आवाज़ का एक नमूना है।",  # noqa: E501
+    "i": "Questo è un esempio della voce selezionata.",
+    "j": "これは選択した声のサンプルです。",  # noqa: E501
+    "p": "Este é um exemplo da voz selecionada.",
+    "z": "这是所选语音的示例。",
+}