Views
No views yet
| Model card | Example |
|---|---|
| English (American) | Link |
| English (British) | Link |
| English (Indian) | Link |
| English (Australian) | Link |
| English (Default) | Link |
| Spanish | Link |
| French | Link |
| Chinese (mix EN) | Link |
| Japanese | Link |
| Korean | Link |
mixed Chinese and English.CPU real-time inference.1from melo.api import TTS
2
3# Speed is adjustable
4speed = 1.0
5
6# CPU is sufficient for real-time inference.
7# You can also change to cuda:0
8device = 'cpu'
9
10text = "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante."
11model = TTS(language='ES', device=device)
12speaker_ids = model.hps.data.spk2id
13
14output_path = 'es.wav'
15model.tts_to_file(text, speaker_ids['ES'], output_path, speed=speed)