SpeechConfig
@PublicPreviewAPI
class SpeechConfig
Speech configuration class for controlling the model's speech and audio generation behaviors.
This allows you to configure the voice properties (single-speaker OR multi-speaker setup) and language preferences when requesting the model to generate spoken responses.
Summary
Public constructors |
|---|
SpeechConfig(Constructs a |
SpeechConfig(voice: Voice, languageCode: String?)Constructs a |
Public properties |
|
|---|---|
String? |
The optional IETF BCP-47 language code (such as |
MultiSpeakerVoiceConfig? |
The multi-speaker configuration. |
Voice? |
The single-speaker |
Public constructors
SpeechConfig
SpeechConfig(
multiSpeakerVoiceConfig: MultiSpeakerVoiceConfig,
languageCode: String? = null
)
Constructs a SpeechConfig for a multi-speaker setup.
Note: Multi-speaker configurations are not supported by the Live API (like LiveGenerationConfig).
| Parameters | |
|---|---|
multiSpeakerVoiceConfig: MultiSpeakerVoiceConfig |
The configuration detailing multiple speakers and their corresponding voices. |
languageCode: String? = null |
An optional IETF BCP-47 language code to guide speech generation. |
SpeechConfig
SpeechConfig(voice: Voice, languageCode: String? = null)
Constructs a SpeechConfig for a single-speaker setup.
Public properties
languageCode
val languageCode: String?
The optional IETF BCP-47 language code (such as "en-US", "es-ES") used to guide the model's speech synthesis and recognition.
multiSpeakerVoiceConfig
val multiSpeakerVoiceConfig: MultiSpeakerVoiceConfig?
The multi-speaker configuration. Note that this configuration is not supported by the Live API (like LiveGenerationConfig).