Make your Pi speak with Google Wavenet voice - node-red-contrib-wavenet

Share Your Nodes
1

Make your Pi speak with Google Wavenet voice.

Wavenet voice represents a new way of creating synthetic speech, using a WaveNet model, the same technology used to produce speech for Google Assistant, Google Search, and Google Translate.

Takes a string as an input. Returns a base64 encoded array buffer. Attach a file node to save it as an MP3 on your disk.

Get it here.
You'll need an API key that you can get at this link - https://cloud.google.com/text-to-speech/

1 Like
2

Don't you think you should mention in the README that you need a Google speech API key?

3

Will do. Updated the post .

4

Hi,

I try to use the wavenet node but I'm not able to creat a playable MP3 File, but I can't figure out what I'm doing wrong.
The API Key is correct since the Wavenet Node outputs an buffer array and the file node creats the file in question, but none player is able to play the new created file. @balsimpson can you, or someone else help me find my mistake?

image
image548Ă—702 36.4 KB

image
image566Ă—556 33.7 KB

found it... encoding in the file node has to be default and not base64