Configuration for a multi-speaker text-to-speech setup. Enables the use of up to two distinct voices in a single synthesis request.
JSON representation |
---|
{
"speakerVoiceConfigs": [
{
object ( |
Fields | |
---|---|
speakerVoiceConfigs[] |
Required. A list of configurations for the voices of the speakers. Exactly two speaker voice configurations must be provided. |
MultispeakerPrebuiltVoice
Configuration for a single speaker in a Gemini TTS multi-speaker setup. Enables dialogue between two speakers.
JSON representation |
---|
{ "speakerAlias": string, "speakerId": string } |
Fields | |
---|---|
speakerAlias |
Required. The speaker alias of the voice. This is the user-chosen speaker name that is used in the multispeaker text input, such as "Speaker1". |
speakerId |
Required. The speaker ID of the voice. See https://cloud.google.com/text-to-speech/docs/gemini-tts#voice_options for available values. |