0
votes

Please help me find information on Watson Speech to Text and Text to Speech regarding:

-Sampling rate

-Buffer size

-No of Channels etc.

I am currently using 10KB buffer size for Text to Speech. Do you think its ok or do I need to increase the size.

1
Hi, what do you mean with buffer size? are you doing chunking, websockets? If you are working on a live app and need the lowest latency then try with smaller buffer sizes. For example, sending around 10-20 chunks per second would be a good practice. - Daniel Bolanos

1 Answers

3
votes

You can find information about the sampling rate for the audio that is returned by Text to Speech here:

http://www.ibm.com/watson/developercloud/doc/text-to-speech/http.shtml#sampling

This page of the documentation may also address some of your other questions. I will follow up on some of the other specific issues you mention.