--- title: Google Gemini Live description: 'Integrate Google Gemini Live with the Conversational AI Engine using the Gemini Developer API. ' sidebar_position: 3 platform: android exported_from: https://docs.agora.io/en/conversational-ai/models/mllm/gemini exported_on: '2026-06-05T05:02:38.634319Z' exported_file: gemini.md --- > For a complete site index fetch https://docs.agora.io/llms.txt. For all pages in this product fetch https://docs.agora.io/en/conversational-ai/overview/product-overview.md [HTML Version](https://docs.agora.io/en/conversational-ai/models/mllm/gemini) # Google Gemini Live Google Gemini Live provides multimodal large language model capabilities with real-time audio processing, enabling natural voice conversations without separate ASR/TTS components. This page covers integration using the Gemini Developer API, authenticated with a Gemini API key obtained from Google AI Studio. > ℹ️ **Info** > Enabling MLLM automatically disables ASR, LLM, and TTS since the MLLM handles end-to-end voice processing directly. ### Sample configuration The following example shows a starting `mllm` parameter configuration you can use when you [Start a conversational AI agent](https://docs-md.agora.io/en/conversational-ai/rest-api/agent/join.md). ```json "mllm": { "enable": true, "api_key": "", "messages": [ { "role": "user", "content": "" } ], "params": { "model": "gemini-3.1-flash-live-preview", "instructions": "You are a friendly assistant.", "voice": "Charon", "affective_dialog": false, "proactive_audio": false, "transcribe_agent": true, "transcribe_user": true, "http_options": { "api_version": "v1beta" } }, "turn_detection": { // see details below }, "input_modalities": [ "audio" ], "output_modalities": [ "audio" ], "greeting_message": "Hi, how can I assist you today?", "failure_message": "Sorry, I encountered an issue. Please try again.", "vendor": "gemini" } ``` ### Turn detection To set up turn detection, add a `turn_detection` block inside the `mllm` object when you [Start a conversational AI agent](https://docs-md.agora.io/en/conversational-ai/rest-api/agent/join.md). > ℹ️ **Info** > When `mllm.turn_detection` is defined, the top-level `turn_detection` object has no effect. The following examples show the supported configurations for Google Gemini Live. * **Server VAD** ```json "turn_detection": { "mode": "server_vad", "server_vad_config": { "prefix_padding_ms": 800, "silence_duration_ms": 640, "start_of_speech_sensitivity": "START_SENSITIVITY_HIGH", "end_of_speech_sensitivity": "END_SENSITIVITY_HIGH" } } ``` * **Agora VAD** ```json "turn_detection": { "mode": "agora_vad", "agora_vad_config": { "interrupt_duration_ms": 160, "prefix_padding_ms": 800, "silence_duration_ms": 640, "threshold": 0.5 } } ``` ### Key parameters **mllm** - **enable** (boolean, optional): Enables the MLLM module. Replaces the deprecated `advanced_features.enable_mllm`. - **api_key** (string, required): The Google Gemini API key used to authenticate requests. You can generate an API key in [Google AI Studio](https://aistudio.google.com/apikey). - **messages** (array[object], optional): An array of conversation history items passed to the model as context. Each item represents a single message in the conversation history. - **role** (string, required): The role of the message author. For example, `system` or `user`. - **content** (string, required): The content of the message. - **params** (object, required): Configuration object for the Gemini Live model. - **model** (string, required): The Gemini Live model identifier. - **instructions** (string, optional): System instructions that define the agent's behavior or tone. - **voice** (string, optional): The voice identifier for audio output. For example, `Aoede`, `Puck`, `Charon`, `Kore`, `Fenrir`, `Leda`, `Orus`, or `Zephyr`. - **affective_dialog** (boolean, optional): Whether to enable affective dialog, which allows the model to adapt its tone based on the user's emotional cues. - **proactive_audio** (boolean, optional): When enabled, the model may choose not to respond if the user's input does not require a reply, such as background speech or incomplete requests. - **transcribe_agent** (boolean, optional): Whether to transcribe the agent's speech in real time. - **transcribe_user** (boolean, optional): Whether to transcribe the user's speech in real time. - **http_options** (object, optional): HTTP request options for the Gemini Live API. - **api_version** (string, optional): The API version to use. For example, `v1beta`. - **turn_detection** (object, optional): Turn detection configuration for the MLLM module. For a full list of `turn_detection` parameters, see [`mllm.turn_detection`](https://docs-md.agora.io/en/conversational-ai/rest-api/agent/join.md). - **mode** (string, optional, possible values: `agora_vad`, `server_vad`): - `agora_vad`: Agora VAD-based detection. - `server_vad`: Vendor-side VAD-based detection. - **agora_vad_config** (object, optional): Configuration for Agora VAD-based turn detection. Applicable when `mode` is `agora_vad`. - **interrupt_duration_ms** (integer, optional): Minimum duration of speech in milliseconds required to trigger an interruption. - **prefix_padding_ms** (integer, optional): Duration of audio in milliseconds to include before the detected speech start. - **silence_duration_ms** (integer, optional): Duration of silence in milliseconds required to determine end of speech. - **threshold** (number, optional): VAD sensitivity threshold. A higher value reduces false positives. - **server_vad_config** (object, optional): Configuration for vendor-side VAD-based turn detection. Applicable when `mode` is `server_vad`. Parameters are passed through to the vendor. - **prefix_padding_ms** (integer, optional): Duration of audio in milliseconds to include before the detected speech start. - **silence_duration_ms** (integer, optional): Duration of silence in milliseconds required to determine end of speech. - **start_of_speech_sensitivity** (string, optional, possible values: `START_SENSITIVITY_HIGH`, `START_SENSITIVITY_LOW`): Sensitivity for start of speech detection. - **end_of_speech_sensitivity** (string, optional, possible values: `END_SENSITIVITY_HIGH`, `END_SENSITIVITY_LOW`): Sensitivity for end of speech detection. - **input_modalities** (array[string], optional, default: `["audio"]`): Input modalities for the MLLM. - `["audio"]`: Audio-only input - `["audio", "text"]`: Accept both audio and text input - **output_modalities** (array[string], optional, default: `["audio"]`): Output modalities for the MLLM. - `["audio"]`: Audio-only output - `["text", "audio"]`: Combined text and audio output - **greeting_message** (string, optional): The message the agent speaks when a user joins the channel. - **failure_message** (string, optional): The message the agent speaks when an error occurs. - **vendor** (string, required): The MLLM provider identifier. Set to `"gemini"` to use Google Gemini Live with the Gemini Developer API. For comprehensive API reference, real-time capabilities, and detailed parameter descriptions, see the [Google Gemini Live API](https://ai.google.dev/api/live).