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>
4 lines
152 B
Python
4 lines
152 B
Python
from .model_info import VOICES, LANGUAGES, MODEL_REPO_ID
|
|
from .loader import VoxtralLoader
|
|
from .audio_utils import numpy_to_comfyui_audio, empty_audio
|