Amazon Polly changes intonation during playing audio.

0

Hello,

Amazon Polly changes intonation during playing audio. Step to reproduce:

  1. Open https://us-west-2.console.aws.amazon.com/polly/home/SynthesizeSpeech?region=us-west-2#
  2. Choose voice Matthew, Male
  3. Turn on SSML
  4. Try to play this:
<speak>
"Hold it up to the light."I did so, and saw a large "E" with a small "g," a "P," and a large "G" with a small "t" woven into the texture of the paper. "What do you make of that?"
</speak>

You can hear that second sentence playing with different intonation. This issue is related to each voice from the list of voices. If you remove from the second sentence "g," a "P," then intonation does not change.

Thanks.

asked 2 years ago354 views
1 Answer
0

Have you used prosody tag [1] ? It is something that is recommended to control the Volume, Speaking Rate, and Pitch. I believe you can use the prosody tag with the right attribute to set the pitch (Value) on here.

For example: pitch

default: Resets pitch to the default level for the current voice.

x-low, low, medium, high, x-high: Sets the pitch to a predefined value for the current voice.

+n% or -n%: Adjusts pitch by a relative percentage. For example, a value of +0% means no baseline pitch change, +5% gives a little higher baseline pitch, and -5% results in a little lower baseline pitch.

You can try the above variations and check if you are able to get the intonation desired.

Regarding checking the audio in the account. I do not believe anyone will have the permission to view the same, except if you can open the case with AWS Support.

Link- https://docs.aws.amazon.com/polly/latest/dg/supportedtags.html#prosody-tag -- [1]

profile pictureAWS
SUPPORT ENGINEER
answered 2 years ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Guidelines for Answering Questions