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?
sarhugo
commented
4 weeks ago
The Text to Speech request/response and streaming response endpoints both allow for a
pronunciation_dictionary_locatorsfield 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?