autogen.agentchat.realtime.experimental.clients.GeminiRealtimeClient

GeminiRealtimeClient

GeminiRealtimeClient(
    *,
    llm_config: LLMConfig | dict[str, Any],
    logger: Logger | None = None
)

(Experimental) Client for Gemini Realtime API.
(Experimental) Client for Gemini Realtime API.

Parameters:

Name	Description
llm_config	Type: LLMConfig | dict[str, typing.Any]
logger	Type: logging.Logger | None Default: None

Static Methods

get_factory

get_factory(
    llm_config: LLMConfig | dict[str, Any],
    logger: Logger,
    **kwargs: Any
) -> 

Create a Realtime API client.

Parameters:

Name	Description
llm_config	The LLM config for the client. Type: LLMConfig | dict[str, typing.Any]
logger	The logger for the client. Type: logging.Logger
**kwargs	Additional arguments. Type: Any

Instance Attributes

connection

Get the Gemini WebSocket connection.

logger

Get the logger for the Gemini Realtime API.

Instance Methods

add_event

add_event(self, event: RealtimeEvent | None) -> 

Parameters:

Name	Description
event	Type: RealtimeEvent | None

connect

connect(self) -> AsyncGenerator[None, None]

Connect to the Gemini Realtime API.

get_event

get_event(self) -> RealtimeEvent | None

queue_input_audio_buffer_delta

queue_input_audio_buffer_delta(self, audio: str) -> None

queue InputAudioBufferDelta.

Parameters:

Name	Description
audio	The audio. Type: str

read_events

read_events(self) -> AsyncGenerator[RealtimeEvent, None]

Read Events from the Gemini Realtime Client

send_audio

send_audio(self, audio: str) -> None

Send audio to the Gemini Realtime API.

Parameters:

Name	Description
audio	The audio to send. Type: str

send_function_result

send_function_result(
    self,
    call_id: str,
    result: str
) -> None

Send the result of a function call to the Gemini Realtime API.

Parameters:

Name	Description
call_id	The ID of the function call. Type: str
result	The result of the function call. Type: str

send_text

send_text(
    self,
    *,
    role: Literal['user', 'assistant', 'system'],
    text: str,
    turn_complete: bool = True
) -> None

Send a text message to the Gemini Realtime API.

Parameters:

Name	Description
role	The role of the message. Type: Literal[‘user’, ‘assistant’, ‘system’]
text	The text of the message. Type: str
turn_complete	A flag indicating if the turn is complete. Type: bool Default: True

session_update

session_update(self, session_options: dict[str, Any]) -> None

Record session updates to be applied when the connection is established.

Parameters:

Name	Description
session_options	The session options to update. Type: dict[str, typing.Any]

truncate_audio

truncate_audio(
    self,
    audio_end_ms: int,
    content_index: int,
    item_id: str
) -> None

Parameters:

Name	Description
audio_end_ms	Type: int
content_index	Type: int
item_id	Type: str