Quick TTS - one-line text-to-speech
Description
Loads model if needed and generates speech. Convenient for quick tests.
Usage
quick_tts(
text,
reference_audio,
output_path = NULL,
device = "cpu",
autocast = NULL
)
Arguments
text: Text to synthesizereference_audio: Path to reference audio fileoutput_path: Optional output file path. If NULL, returns audio data.device: Device to useautocast: Use mixed precision (float16) on CUDA (default TRUE on CUDA)
Value
If output_path is NULL, returns list with audio and sample_rate. Otherwise writes to file and returns path invisibly.