LiveConnectConfig

Configures the avatar model behavior.

Configures context window compression mechanism.

If enabled, the model will detect emotions and adapt its responses accordingly.

Configures the explicit VAD signal. If enabled, the client will send vad_signal to indicate the start and end of speech. This allows the server to process the audio more efficiently.

Used to override HTTP request options.

The transcription of the input aligns with the input audio language.

Maximum number of tokens that can be generated in the response.

If specified, the media resolution specified will be used.

The transcription of the output aligns with the language code specified for the output audio.

Configures the proactivity of the model. This allows the model to respond proactively to the input and to ignore irrelevant input.

Configures the realtime input behavior in BidiGenerateContent.

The requested modalities of the response. Represents the set of modalities that the model can return. Defaults to AUDIO if not specified.

Safety settings in the request to block unsafe content in the response.

When `seed` is fixed to a specific number, the model makes a best effort to provide the same response for repeated requests. By default, a random number is used.

Configures session resumption mechanism.

The speech generation configuration.

The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.

Value that controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a less open-ended or creative response, while higher temperatures can lead to more diverse or creative results.

Config for thinking features. An error will be returned if this field is set for models that don't support thinking.

A list of Tools the model may use to generate the next response.

For each token selection step, the `top_k` tokens with the highest probabilities are sampled. Then tokens are further filtered based on `top_p` with the final token selected using temperature sampling. Use a lower number for less random responses and a higher number for more random responses.

Tokens are selected from the most to least probable until the sum of their probabilities equals this value. Use a lower value for less random responses and a higher value for more random responses.

Config for translation.