OpenAI Realtime API

OpenAI Realtime provides multimodal large language model capabilities with real-time audio processing, enabling natural voice conversations without separate ASR/TTS components.

To enable MLLM functionality, set enable_mllm to true under advanced_features.

_3

"advanced_features": {

_3

"enable_mllm": true

_3

}

The following example shows a starting mllm parameter configuration you can use when you Start a conversational AI agent.

_19

"mllm": {

_19

"url": "wss://api.openai.com/v1/realtime",

_19

"api_key": "<openai_api_key>",

_19

"params": {

_19

"model": "gpt-4o-realtime-preview",

_19

"voice": "coral",

_19

"instructions": "You are a Conversational AI Agent, developed by Agora.",

_19

"input_audio_transcription": {

_19

"language": "<language>",

_19

"model": "gpt-4o-mini-transcribe",

_19

"prompt": "expect words related to real-time engagement"

_19

}

_19

},

_19

"max_history": 50,

_19

"greeting_message": "<greetings>",

_19

"output_modalities": ["text", "audio"],

_19

"vendor": "openai",

_19

"style": "openai"

_19

}

mllmrequired

• url stringrequired

  The WebSocket URL for OpenAI Realtime API.

• api_key stringrequired

  The API key used for authentication. Get your API key from the OpenAI Console.

• messages array[object]nullable

  Array of conversation items used for short-term memory management. Uses the same structure as item.content from the OpenAI Realtime API.

• params objectnullable

  Additional MLLM configuration parameters.

  • Modalities override: The modalities setting in params is overridden by input_modalities and output_modalities.
  • Turn detection override: The turn_detection setting in params is overridden by the turn_detection section outside of mllm.
    See MLLM Overview for details.

  Show propertiesHide properties

  • model stringnullable

    The model identifier.

  • voice stringnullable

    The voice identifier for audio output.

  • instructions stringnullable

    System instructions that define the assistant's behavior and personality.

  • input_audio_transcription objectnullable

    Configuration for audio input transcription.

    Show propertiesHide properties

    • language stringnullable

      The language of the input audio. Supplying the input language in ISO-639-1 format (For example en) improves accuracy and latency.

    • model stringnullable

      The model to use for transcription. Current options are gpt-4o-transcribe, gpt-4o-mini-transcribe, and whisper-1.

    • prompt stringnullable

      An optional text to guide the model's style or continue a previous audio segment. For whisper-1, the prompt is a list of keywords. For gpt-4o-transcribe models, the prompt is a free text string, for example "expect words related to technology".

• max_history integernullable

  Default: 32

  The number of conversation history messages to maintain. Cannot exceed the model's context window.

• input_modalities array[string]nullable

  Default: ["audio"]

  MLLM input modalities:

  • ["audio"]: Audio only
  • ["audio", "text"]: Audio plus text
• output_modalities array[string]nullable

  Default: ["text", "audio"]

  Output format options: ["text", "audio"] for both text and voice responses.

• greeting_message stringnullable

  Initial message the agent speaks when a user joins the channel.

• vendor stringnullable

  MLLM provider identifier. Set to openai for OpenAI Realtime API.

• style stringnullable

  API request style. Set to openai for OpenAI Realtime API format.

For comprehensive API reference, real-time capabilities, and detailed parameter descriptions, see the OpenAI Realtime API documentation.