TTS Audio Suite

TTS Audio Suite requires a minimum of 1536MB (1.5GB) of VRAM for base operation. For optimal performance, a GPU with at least 6GB of VRAM is recommended. This node supports low VRAM mode for resource-constrained setups.

✅ RTX 3060 (12GB): Yes, fully compatible with 9.3GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 9.3GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 12.9GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 20.1GB headroom

On an RTX 3060 (12GB VRAM), TTS Audio Suite runs smoothly on an RTX 3060 (12GB) with 9.3GB of headroom. This is sufficient to run the node alongside standard SD 1.5 and SDXL workflows in full precision. On an RTX 4090 (24GB VRAM), the node runs with extreme headroom on an RTX 4090 (24GB) with 20.1GB of dedicated headroom. This allows you to combine the node with massive models (like FLUX.1 Dev, Schnell, or Hunyuan Video) in full precision (FP16) without any offload flags.

TTS Audio Suite requires the following PyTorch-related packages: ema-pytorch# F5-TTS exponential moving average, torch>=2.0.0, torchaudio>=2.0.0, torchdiffeq# F5-TTS differential equations, torchfcpe>=0.0.4 # Fast Context-based Pitch Estimation for RVC (fcpe method). Ensure your ComfyUI environment has these installed. Ensure your PyTorch installation matches your CUDA version (use torch.version.cuda to check).

To run TTS Audio Suite, you need to install: accelerate, av>=12.0.0 # DramaBox official audio reference decoding, bitsandbytes>=0.47.0 # 4-bit quantization support for VibeVoice memory efficiency, cn2an>=0.5.22 # Chinese number to Arabic number conversion, conformer>=0.3.2 # ChatterBox engine, dacite, datasets, echo-tts, einops>=0.7.0 # DramaBox LTX tensor rearrangement, ema-pytorch# F5-TTS exponential moving average, faiss-cpu>=1.7.4, ftfy# MOSS-SoundEffect v2 prompt normalization, funasr>=1.1.3 # FunASR speech processing toolkit, g2p-en>=2.1.0 # English grapheme-to-phoneme conversion, hyperpyyaml# YAML configuration parser, inflect>=7.3.0 # Text normalization for English (used in frontend.py), jieba, json5>=0.12.0 # JSON5 parsing for IndexTTS-2 config files, keras>=2.9.0 # Deep learning framework, langcodes, lingua-language-detector, loguru, modelscope>=1.27.0 # Chinese model hub for IndexTTS-2, monotonic-alignment-search, munch>=4.0.0 # Dictionary access with dot notation, nagisa>=0.2.11 # Japanese tokenizer required by Qwen3-ASR forced aligner, ninja>=1.11.0 # Build tool for CUDA kernel compilation (BigVGAN optimization), numpy>=1.26.4,<2.3.0 # Compatible with both numpy 1.26.4 and 2.x series, omegaconf>=2.3.0, openai-whisper# Mel spectrogram extraction for audio tokenizer, orjson>=3.11.0 # MOSS-TTS remote-code dependency, peft>=0.18.1 # MOSS-TTS LoRA adapter inference/training support (aLoRA/Arrow-era adapter configs), phonemizer# IPA phonemization for multilingual TTS (requires espeak system dependency), praat-parselmouth>=0.4.6 # Praat-based f0 extraction for RVC (pm method), protobuf>=3.20.0 # Protocol buffers (compatible with descript-audiotools), punctuators# ONNX punctuation/truecase post-processing for ASR text, pydub, pypinyin, pyworld>=0.3.5 # World vocoder for RVC harvest/dio methods, pyyaml>=6.0 # DramaBox/LTX configuration support, requests, safetensors>=0.6.2 # MOSS-TTS / HF safetensors checkpoints, sentencepiece>=0.2.1 # Text tokenization, setuptools>=65.0.0 # Provides distutils compatibility for Python 3.12+ (required by FunASR bundled code), sounddevice>=0.4.0, soundfile>=0.12.0, textstat>=0.7.10 # Text statistics and readability, tiktoken>=0.12.0 # MOSS-TTS tokenizer dependency, torch>=2.0.0, torchaudio>=2.0.0, torchdiffeq# F5-TTS differential equations, torchfcpe>=0.0.4 # Fast Context-based Pitch Estimation for RVC (fcpe method), transformers>=5.3.0,<6.0.0 # Main environment for Higgs Audio v3 / Step Audio EditX / MOSS-TTS. Legacy Transformers 4 engines use isolated runtimes., unidecode, vocos# F5-TTS vocoder, wandb# F5-TTS logging, webdataset, x-transformers. You can install these using pip or add them to your requirements.txt file.

TTS Audio Suite supports low VRAM mode. To reduce memory usage: (1) Enable --lowvram or --medvram flags in ComfyUI, (2) Reduce batch size to 1, (3) Use fp16 or fp8 precision if supported, (4) Close other GPU applications.

To install TTS Audio Suite: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/diodiogod/TTS-Audio-Suite, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.