filliptmandClaude Opus 4.6
60f6897263
Custom node pack implementing Mistral's Voxtral-4B-TTS-2603 model with direct PyTorch inference (no vLLM dependency), enabling native MPS/Mac support alongside CUDA. Three-component architecture: - Mistral LLM backbone (26 layers, 3072 dim, GQA, RoPE) - Flow-matching acoustic transformer (3 layers, 8-step Euler ODE, CFG) - Neural audio codec decoder (4-stage ALiBi transformer + conv upsampling) Features: - 20 preset voices across 9 languages - 24 kHz mono output - BF16/FP16/FP32 dtype support - HuggingFace Hub auto-download with caching - ComfyUI AUDIO output format Nodes: - FL_VoxtralTTS_ModelLoader: download and load model - FL_VoxtralTTS_Generate: text + voice → audio Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
46 lines
788 B
Python
46 lines
788 B
Python
MODEL_REPO_ID = "mistralai/Voxtral-4B-TTS-2603"
|
|
|
|
VOICES = [
|
|
"casual_female",
|
|
"casual_male",
|
|
"cheerful_female",
|
|
"neutral_female",
|
|
"neutral_male",
|
|
"fr_female",
|
|
"fr_male",
|
|
"es_female",
|
|
"es_male",
|
|
"de_female",
|
|
"de_male",
|
|
"it_female",
|
|
"it_male",
|
|
"pt_female",
|
|
"pt_male",
|
|
"nl_female",
|
|
"nl_male",
|
|
"ar_male",
|
|
"hi_female",
|
|
"hi_male",
|
|
]
|
|
|
|
LANGUAGES = [
|
|
"English",
|
|
"French",
|
|
"Spanish",
|
|
"German",
|
|
"Italian",
|
|
"Portuguese",
|
|
"Dutch",
|
|
"Arabic",
|
|
"Hindi",
|
|
]
|
|
|
|
# Device detection
|
|
def get_default_device():
|
|
import torch
|
|
if torch.cuda.is_available():
|
|
return "cuda"
|
|
if hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
|
|
return "mps"
|
|
return "cpu"
|