elevenlabs-python icon indicating copy to clipboard operation
elevenlabs-python copied to clipboard
verified publisher icon elevenlabs

Missing feature: Pronunciation dictionary with Text to Speech Websocket connection

Open JesusGuzmanJr opened this issue 1 year ago • 2 comments

The Text to Speech request/response and streaming response endpoints both allow for a pronunciation_dictionary_locators field in the request body. The bidirectional streaming Websocket endpoint however doesn't seem to support this.

Is there a plan to add pronunciation dictionaries to Websocket Text to Speech in the future?

JesusGuzmanJr avatar May 19 '24 19:05 JesusGuzmanJr

+1

sarhugo avatar Jun 04 '24 01:06 sarhugo

+1 this would be useful

rizhangdev avatar Sep 29 '24 01:09 rizhangdev

+1. Would like to use pronunciation dictionaires with the streaming web sockets TTS endpoint — can this support be added?

esteban-btc avatar Nov 19 '24 00:11 esteban-btc

hi! we are going to be using this issues page to only monitor issues with our python SDK but i have logged this and will actively work on implementing this for you all soon! thanks for the request!

AngeloGiacco avatar Feb 03 '25 19:02 AngeloGiacco

Thank you for the update @AngeloGiacco do you have a timeline of when this will be implemented?

Bilal-io avatar Feb 04 '25 18:02 Bilal-io