StreamingSynthesisInput

JSON representation

Input to be synthesized.

JSON representation

JSON representation
{ // Union field `input_source` can be only one of the following: "text" : string , "markup" : string , "multiSpeakerMarkup" : { object ( `MultiSpeakerMarkup` ) } // End of list of possible types for union field `input_source` . "prompt" : string }

 { 
 // Union field input_source 
can be only one of the following: 
 "text" 
 : 
 string 
 , 
 "markup" 
 : 
 string 
 , 
 "multiSpeakerMarkup" 
 : 
 { 
 object (  MultiSpeakerMarkup 
 
) 
 } 
 // End of list of possible types for union field input_source 
. 
 "prompt" 
 : 
 string 
 }

Fields

Union field input_source .

input_source can be only one of the following:

text

string

The raw text to be synthesized. It is recommended that each input contains complete, terminating sentences, which results in better prosody in the output audio.

markup

string

Markup for HD voices specifically. This field may not be used with any other voices.

multiSpeakerMarkup

object ( MultiSpeakerMarkup )

Multi-speaker markup for Gemini TTS. This field may not be used with any other voices.

prompt

string

This is system instruction supported only for controllable voice models.

StreamingSynthesisInput Stay organized with collections Save and categorize content based on your preferences.

StreamingSynthesisInput