Download link
Google Wavenet Text-to-Speech (TTS) service uses advanced deep learning technologies of Google Cloud Platform to synthesize natural sounding human speech With over 310 different lifelike voices across more than 49 languages and dialects, you can synthesize text in various language easily. With Google Wavenet you can merge multiple voices and create a single synthesize task with one click.
In addition to Standard TTS voices, Google offers WaveNet voices that deliver advanced improvements in speech quality through a new machine learning approach.
Enjoy convenient usage of SSML tags to add various voice effects, such as adjusting pitch, volume, speed, emphasis, word or phrase beep outs to name a few. Full list can be found on demo upon selecting respective voices.
Google Wavenet Text-to-Speech (TTS) service uses advanced deep learning technologies of Google Cloud Platform to synthesize natural sounding human speech With over 310 different lifelike voices across more than 49 languages and dialects, you can synthesize text in various language easily. With Google Wavenet you can merge multiple voices and create a single synthesize task with one click.
In addition to Standard TTS voices, Google offers WaveNet voices that deliver advanced improvements in speech quality through a new machine learning approach.
Enjoy convenient usage of SSML tags to add various voice effects, such as adjusting pitch, volume, speed, emphasis, word or phrase beep outs to name a few. Full list can be found on demo upon selecting respective voices.
