MeloTTS/README.md

 

Introduction

MyShellTTSBase is a high-quality multi-lingual text-to-speech library. Example languages include:

Language	Example
English	Link
English (American)	Link
English (British)	Link
English (India)	Link
English (Australian)	Link
Spanish	Link
French	Link
Chinese (mix EN)	Link
Japanese	Link
Korean	Link

The Chinese speaker supports mixed Chinese and English.

Install

git clone git@github.com:myshell-ai/MyShellTTSBase.git
cd MyShellTTSBase
python setup.py install

Usage

English with Multi Accents

from MyShellTTSBase.api import TTS

# Speed is adjustable
speed = 1.0

# English 
text = "Did you ever hear a folk tale about a giant turtle?"
model = TTS(language='EN')
speaker_ids = model.hps.data.spk2id

# Default accent
output_path = 'en-default.wav'
model.tts_to_file(text, speaker_ids['EN-Default'], output_path, speed=speed)

# American accent
output_path = 'en-us.wav'
model.tts_to_file(text, speaker_ids['EN-US'], output_path, speed=speed)

# British accent
output_path = 'en-br.wav'
model.tts_to_file(text, speaker_ids['EN-BR'], output_path, speed=speed)

# Indian accent
output_path = 'en-india.wav'
model.tts_to_file(text, speaker_ids['EN_INDIA'], output_path, speed=speed)

# Australian accent
output_path = 'en-au.wav'
model.tts_to_file(text, speaker_ids['EN-AU'], output_path, speed=speed)

Spanish

from MyShellTTSBase.api import TTS

# Speed is adjustable
speed = 1.0
text = "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante."
model = TTS(language='ES')
speaker_ids = model.hps.data.spk2id

output_path = 'es.wav'
model.tts_to_file(text, speaker_ids['ES'], output_path, speed=speed)

French

from MyShellTTSBase.api import TTS

# Speed is adjustable
speed = 1.0
text = "La lueur dorée du soleil caresse les vagues, peignant le ciel d'une palette éblouissante."
model = TTS(language='FR')
speaker_ids = model.hps.data.spk2id

output_path = 'fr.wav'
model.tts_to_file(text, speaker_ids['FR'], output_path, speed=speed)

Chinese

from MyShellTTSBase.api import TTS

# Speed is adjustable
speed = 1.0
text = "我最近在学习machine learning，希望能够在未来的artificial intelligence领域有所建树。"
model = TTS(language='ZH')
speaker_ids = model.hps.data.spk2id

output_path = 'zh.wav'
model.tts_to_file(text, speaker_ids['ZH'], output_path, speed=speed)

Japanese

from MyShellTTSBase.api import TTS

# Speed is adjustable
speed = 1.0
text = "彼は毎朝ジョギングをして体を健康に保っています。"
model = TTS(language='JP')
speaker_ids = model.hps.data.spk2id

output_path = 'jp.wav'
model.tts_to_file(text, speaker_ids['JP'], output_path, speed=speed)

Korean

from MyShellTTSBase.api import TTS

# Speed is adjustable
speed = 1.0
text = "안녕하세요! 오늘은 날씨가 정말 좋네요."
model = TTS(language='KR')
speaker_ids = model.hps.data.spk2id

output_path = 'kr.wav'
model.tts_to_file(text, speaker_ids['KR'], output_path, speed=speed)

License

This library is under MIT License. Free for both commercial and non-commercial use.

Acknowledgement

This implementation is based on several excellent projects, TTS, VITS, and VITS2. We appreciate their awesome work!