Skip to content
AIMarketCap

WaveNet

Model

DeepMind neural audio-generation model that advanced natural-sounding speech synthesis.

Released
Sep 8, 2016
Context window
—
Modality
—
Open source
—
API available
—
Releases
1

Releases

1
Sep 8, 2016WaveNet research publishedWaveNet

DeepMind introduces WaveNet, a neural generative model for raw audio waveforms that substantially improves speech synthesis.