How to use scrappylabs/narrator-tts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="scrappylabs/narrator-tts")
# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("scrappylabs/narrator-tts", dtype="auto")
How to use scrappylabs/narrator-tts with Qwen3-TTS:
# pip install qwen-tts import torch import soundfile as sf from qwen_tts import Qwen3TTSModel model = Qwen3TTSModel.from_pretrained( "scrappylabs/narrator-tts", device_map="cuda:0", dtype=torch.bfloat16, attn_implementation="flash_attention_2", ) wavs, sr = model.generate_custom_voice( text="Your text here.", language="English", speaker="Ryan", instruct="Speak in a natural tone.", ) sf.write("output.wav", wavs[0], sr)
