You are here: Home » NewsFeeds » An open source implementation of DeepVoice 3: 2000-Speaker Neural Text-to-Speech

An open source implementation of DeepVoice 3: 2000-Speaker Neural Text-to-Speech

This page provides audio samples for the open source implementation of DeepVoice3. Samples from single speaker and multi-speaker models follow.

Single speaker

Scientists at the CERN laboratory say they have discovered a new particle.

(74 chars, 13 words)

Your browser does not support the audio element.

There’s a way to measure the acute emotional intelligence that has never gone out of style.

(91 chars, 18 words)

Your browser does not support the audio element.

President Trump met with other leaders at the Group of 20 conference.

(69 chars, 13 words)

Your browser does not support the audio element.

The Senate’s bill to repeal and replace the Affordable Care Act is now imperiled.

(81 chars, 16 words)

Your browser does not support the audio element.

Generative adversarial network or variational auto-encoder.

(59 chars, 7 words)

Your browser does not support the audio element.

The buses aren’t the problem, they actually provide a solution.

(63 chars, 13 words)

Your browser does not support the audio element.

Multi-speaker

Samples from a model trained for


 

Original article