14 lines
485 B
Python
14 lines
485 B
Python
import torchaudio as ta
|
|
from chatterbox.tts import ChatterboxTTS
|
|
|
|
model = ChatterboxTTS.from_pretrained(device="mps")
|
|
|
|
text = "Sometimes you have to wonder just what's going on with this crazy fucking world."
|
|
#wav = model.generate(text)
|
|
#ta.save("test-1.wav", wav, model.sr)
|
|
|
|
# If you want to synthesize with a different voice, specify the audio prompt
|
|
AUDIO_PROMPT_PATH="sample.mp3"
|
|
wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH)
|
|
ta.save("test-2.wav", wav, model.sr)
|