Metadata-Version: 2.1
Name: tts-audio-suite
Version: 4.25.9
Summary: TTS Audio Suite - Universal multi-engine TTS extension for ComfyUI with unified architecture supporting IndexTTS-2, ChatterBox, Chatterbox Multilingual TTS (Official 23-Lang), F5-TTS, Higgs Audio 2, VibeVoice, and RVC engines. It has character voice management, SRT subtitle TTS support, and audio processing capabilities.
Home-page: https://github.com/diodiogod/TTS-Audio-Suite
Requires-Python: >=3.10
Requires-Dist: numpy
Requires-Dist: setuptools>=65.0.0    # Provides distutils compatibility for Python 3.12+ (required by FunASR bundled code)
Requires-Dist: soundfile>=0.12.0
Requires-Dist: sounddevice>=0.4.0
Requires-Dist: jieba
Requires-Dist: pypinyin
Requires-Dist: unidecode
Requires-Dist: phonemizer              # IPA phonemization for multilingual TTS (requires espeak system dependency)
Requires-Dist: omegaconf>=2.3.0
Requires-Dist: transformers>=4.51.3,<=4.57.3  # Required for VibeVoice compatibility (4.51.3+). Transformers 5.0.0 breaks Qwen3-TTS tokenizer loading.
Requires-Dist: accelerate
Requires-Dist: datasets
Requires-Dist: requests
Requires-Dist: dacite
Requires-Dist: bitsandbytes>=0.47.0     # 4-bit quantization support for VibeVoice memory efficiency
Requires-Dist: conformer>=0.3.2      # ChatterBox engine
Requires-Dist: x-transformers
Requires-Dist: torchdiffeq          # F5-TTS differential equations
Requires-Dist: wandb                # F5-TTS logging
Requires-Dist: ema-pytorch          # F5-TTS exponential moving average
Requires-Dist: vocos                # F5-TTS vocoder
Requires-Dist: echo-tts
Requires-Dist: cn2an>=0.5.22         # Chinese number to Arabic number conversion
Requires-Dist: g2p-en>=2.1.0         # English grapheme-to-phoneme conversion
Requires-Dist: keras>=2.9.0          # Deep learning framework
Requires-Dist: modelscope>=1.27.0    # Chinese model hub for IndexTTS-2
Requires-Dist: munch>=4.0.0          # Dictionary access with dot notation
Requires-Dist: json5>=0.12.0         # JSON5 parsing for IndexTTS-2 config files
Requires-Dist: ninja>=1.11.0         # Build tool for CUDA kernel compilation (BigVGAN optimization)
Requires-Dist: sentencepiece>=0.2.1  # Text tokenization
Requires-Dist: textstat>=0.7.10      # Text statistics and readability
Requires-Dist: punctuators           # ONNX punctuation/truecase post-processing for ASR text
Requires-Dist: openai-whisper        # Mel spectrogram extraction for audio tokenizer
Requires-Dist: funasr>=1.1.3         # FunASR speech processing toolkit
Requires-Dist: nagisa>=0.2.11        # Japanese tokenizer required by Qwen3-ASR forced aligner
Requires-Dist: hyperpyyaml           # YAML configuration parser
Requires-Dist: protobuf
Requires-Dist: monotonic-alignment-search
Requires-Dist: faiss-cpu>=1.7.4
Requires-Dist: praat-parselmouth>=0.4.6  # Praat-based f0 extraction for RVC (pm method)
Requires-Dist: pyworld>=0.3.5           # World vocoder for RVC harvest/dio methods
Requires-Dist: torchfcpe>=0.0.4         # Fast Context-based Pitch Estimation for RVC (fcpe method)
Requires-Dist: inflect>=7.3.0           # Text normalization for English (used in frontend.py)
