Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
Paper • 1712.05884 • Published • 3
British English, female single-speaker Tacotron2 TTS
model trained on speaker ek1 from the
M-AILABS dataset.
Trained by @nmstoker and originally published at: https://github.com/coqui-ai/TTS/releases/v0.6.1_models/
With Coqui TTS:
from TTS.api import TTS
tts = TTS("tts_models/en/ek1/tacotron2")
tts.tts_to_file("Hello world", file_path="output.wav")