# Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning Source: [Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:56:11.088Z Authors: Wei Ping, Kainan Peng, Andrew Gibiansky, Sercan O. Arik, Ajay Kannan, Sharan Narang, Jonathan Raiman, John Miller Published: 2017-10-20T18:17:23.000Z ## Abstract We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in naturalness while training ten times faster. We scale Deep Voice 3 to data set sizes unprecedented for TTS, training on more than eight hundred hours of audio from over two thousand speakers. In addition, we identify common error modes of attention-based speech synthesis networks, demonstrate how to mitigate them, and compare several different waveform synthesis methods. We also describe how to scale inference to ten million queries per day on one single-GPU server. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Text-to-speech on Internal US English dataset (test)](): Text-to-Speech; Internal US English dataset (test); MOS: 4.001. ## Original sources and implementation [Original paper]() [PDF]()