--- title: "Create client secret" method: POST path: "/realtime/client_secrets" tags: ["Realtime"] --- # Create client secret `POST /realtime/client_secrets` Create a Realtime client secret with an associated session configuration. Client secrets are short-lived tokens that can be passed to a client app, such as a web frontend or mobile client, which grants access to the Realtime API without leaking your main API key. You can configure a custom TTL for each client secret. You can also attach session configuration options to the client secret, which will be applied to any sessions created using that client secret, but these can also be overridden by the client connection. [Learn more about authentication with client secrets over WebRTC](https://platform.openai.com/docs/guides/realtime-webrtc). Returns the created client secret and the effective session object. The client secret is a string that looks like `ek_1234`. ## Request body - RealtimeCreateClientSecretRequest — Create a session and client secret for the Realtime API. The request can specify either a realtime or a transcription session configuration. [Learn more about the Realtime API](https://platform.openai.com/docs/guides/realtime). - `expires_after` object — Configuration for the client secret expiration. Expiration refers to the time after which a client secret will no longer be valid for creating sessions. The session itself may continue after that time once started. A secret can be used to create multiple sessions until it expires. - `anchor` 'created_at' — The anchor point for the client secret expiration, meaning that `seconds` will be added to the `created_at` time of the client secret to produce an expiration timestamp. Only `created_at` is currently supported. - `seconds` integer — The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200` (2 hours). This default to 600 seconds (10 minutes) if not specified. - `session` union — Session configuration to use for the client secret. Choose either a realtime session or a transcription session. - RealtimeSessionCreateRequestGA — Realtime session object configuration. - `type` 'realtime', required — The type of session to create. Always `realtime` for the Realtime API. - `output_modalities` string[] — The set of modalities the model can respond with. It defaults to `["audio"]`, indicating that the model will respond with audio plus a transcript. `["text"]` can be used to make the model respond with text only. It is not possible to request both `text` and `audio` at the same time. - `model` union — The Realtime model used for this session. - string - 'gpt-realtime' | 'gpt-realtime-1.5' | 'gpt-realtime-2' | 'gpt-realtime-2.1' | 'gpt-realtime-2.1-mini' | 'gpt-realtime-2025-08-28' | 'gpt-4o-realtime-preview' | 'gpt-4o-realtime-preview-2024-10-01' | 'gpt-4o-realtime-preview-2024-12-17' | 'gpt-4o-realtime-preview-2025-06-03' | 'gpt-4o-mini-realtime-preview' | 'gpt-4o-mini-realtime-preview-2024-12-17' | 'gpt-realtime-mini' | 'gpt-realtime-mini-2025-10-06' | 'gpt-realtime-mini-2025-12-15' | 'gpt-audio-1.5' | 'gpt-audio-mini' | 'gpt-audio-mini-2025-10-06' | 'gpt-audio-mini-2025-12-15' - `instructions` string — The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. - `audio` object — Configuration for input and output audio. - `input` object - `format` union - object — The PCM audio format. Only a 24kHz sample rate is supported. - … - object — The G.711 μ-law format. - … - object — The G.711 A-law format. - … - `transcription` AudioTranscription - `model` union — The model to use for transcription. Current options are `whisper-1`, `gpt-transcribe`, `gpt-live-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. - … - `language` string — The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency. - `languages` string[] — Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format. Supported by `gpt-transcribe` and `gpt-live-transcribe`. - `keywords` string[] — Words or phrases to guide transcription of the input audio. Supported by `gpt-transcribe` and `gpt-live-transcribe`. - `prompt` string — 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](https://platform.openai.com/docs/guides/speech-to-text#prompting). For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. - `delay` 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' — Controls how long the model waits before emitting transcription text. Higher values can improve transcription accuracy at the cost of latency. Only supported with `gpt-realtime-whisper` in GA Realtime sessions. - `noise_reduction` object — Configuration for input audio noise reduction. This can be set to `null` to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. - `type` 'near_field' | 'far_field' — Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. - `turn_detection` union - object — Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence. - … - object — Server-side semantic turn detection which uses a model to determine when the user has finished speaking. - … - `output` object - `format` union - object — The PCM audio format. Only a 24kHz sample rate is supported. - … - object — The G.711 μ-law format. - … - object — The G.711 A-law format. - … - `voice` union — A built-in voice name or a custom voice reference. - union - … - object — Custom voice reference. - … - `speed` number — The speed of the model's spoken response as a multiple of the original speed. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. This parameter is a post-processing adjustment to the audio after it is generated, it's also possible to prompt the model to speak faster or slower. - `include` string[] — Additional fields to include in server outputs. `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. - `tracing` union — Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. `auto` will create a trace for the session with default values for the workflow name, group id, and metadata. - 'auto' — Enables tracing and sets default values for tracing configuration options. Always `auto`. - object — Granular configuration for tracing. - `workflow_name` string — The name of the workflow to attach to this trace. This is used to name the trace in the Traces Dashboard. - `group_id` string — The group id to attach to this trace to enable filtering and grouping in the Traces Dashboard. - `metadata` object — The arbitrary metadata to attach to this trace to enable filtering in the Traces Dashboard. - `tools` union[] — Tools available to the model. - union - RealtimeFunctionTool - `type` 'function' — The type of the tool, i.e. `function`. - `name` string — The name of the function. - `description` string — The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything). - `parameters` object — Parameters of the function in JSON Schema. - MCPTool — Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). - `type` 'mcp', required — The type of the MCP tool. Always `mcp`. - `server_label` string, required — A label for this MCP server, used to identify it in tool calls. - `server_url` string, uri — The URL for the MCP server. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `connector_id` 'connector_dropbox' | 'connector_gmail' | 'connector_googlecalendar' | 'connector_googledrive' | 'connector_microsoftteams' | 'connector_outlookcalendar' | 'connector_outlookemail' | 'connector_sharepoint' — Identifier for service connectors, like those available in ChatGPT. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` - `tunnel_id` string — The Secure MCP Tunnel ID to use instead of a direct server URL. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `authorization` string — An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. - `server_description` string — Optional description of the MCP server, used to provide more context. - `headers` object, nullable — Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - `allowed_tools` union - … - `allowed_callers` CallableToolAllowedCaller[], nullable — The tool invocation context(s). - `require_approval` union - … - `defer_loading` boolean — Whether this MCP tool is deferred and discovered via tool search. - `tool_choice` union — How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool. - 'none' | 'auto' | 'required' — Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. - ToolChoiceFunction — Use this option to force the model to call a specific function. - `type` 'function', required — For function calling, the type is always `function`. - `name` string, required — The name of the function to call. - ToolChoiceMCP — Use this option to force the model to call a specific tool on a remote MCP server. - `type` 'mcp', required — For MCP tools, the type is always `mcp`. - `server_label` string, required — The label of the MCP server to use. - `name` string, nullable — The name of the tool to call on the server. - `parallel_tool_calls` boolean — Whether the model may call multiple tools in parallel. Only supported by reasoning Realtime models such as `gpt-realtime-2`. - `reasoning` RealtimeReasoning — Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. - `effort` 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' — Constrains effort on reasoning for reasoning-capable Realtime models such as `gpt-realtime-2`. - `max_output_tokens` union — Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or `inf` for the maximum available tokens for a given model. Defaults to `inf`. - integer - 'inf' - `truncation` union — When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. - 'auto' | 'disabled' — The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. - object — Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. - `type` 'retention_ratio', required — Use retention ratio truncation. - `retention_ratio` number, required — Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. - `token_limits` object — Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. - `post_instructions` integer — Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. - `prompt` Prompt, nullable — Reference to a prompt template and its variables. [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). - `id` string, required — The unique identifier of the prompt template to use. - `version` string, nullable — Optional version of the prompt template. - `variables` ResponsePromptVariables, nullable — Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files. - RealtimeTranscriptionSessionCreateRequestGA — Realtime transcription session object configuration. - `type` 'transcription', required — The type of session to create. Always `transcription` for transcription sessions. - `audio` object — Configuration for input and output audio. - `input` object - `format` union - object — The PCM audio format. Only a 24kHz sample rate is supported. - … - object — The G.711 μ-law format. - … - object — The G.711 A-law format. - … - `transcription` AudioTranscription - `model` union — The model to use for transcription. Current options are `whisper-1`, `gpt-transcribe`, `gpt-live-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. - … - `language` string — The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency. - `languages` string[] — Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format. Supported by `gpt-transcribe` and `gpt-live-transcribe`. - `keywords` string[] — Words or phrases to guide transcription of the input audio. Supported by `gpt-transcribe` and `gpt-live-transcribe`. - `prompt` string — 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](https://platform.openai.com/docs/guides/speech-to-text#prompting). For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. - `delay` 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' — Controls how long the model waits before emitting transcription text. Higher values can improve transcription accuracy at the cost of latency. Only supported with `gpt-realtime-whisper` in GA Realtime sessions. - `noise_reduction` object — Configuration for input audio noise reduction. This can be set to `null` to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. - `type` 'near_field' | 'far_field' — Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. - `turn_detection` union - object — Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence. - … - object — Server-side semantic turn detection which uses a model to determine when the user has finished speaking. - … - `include` string[] — Additional fields to include in server outputs. `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. ## Response `200` Client secret created successfully. - RealtimeCreateClientSecretResponse — Response from creating a session and client secret for the Realtime API. - `value` string, required — The generated client secret value. - `expires_at` integer, required — Expiration timestamp for the client secret, in seconds since epoch. - `session` union, required — The session configuration for either a realtime or transcription session. - RealtimeSessionCreateResponseGA — A Realtime session configuration object. - `type` 'realtime', required — The type of session to create. Always `realtime` for the Realtime API. - `id` string, required — Unique identifier for the session that looks like `sess_1234567890abcdef`. - `object` 'realtime.session', required — The object type. Always `realtime.session`. - `expires_at` integer — Expiration timestamp for the session, in seconds since epoch. - `output_modalities` string[] — The set of modalities the model can respond with. It defaults to `["audio"]`, indicating that the model will respond with audio plus a transcript. `["text"]` can be used to make the model respond with text only. It is not possible to request both `text` and `audio` at the same time. - `model` union — The Realtime model used for this session. - string - 'gpt-realtime' | 'gpt-realtime-1.5' | 'gpt-realtime-2' | 'gpt-realtime-2.1' | 'gpt-realtime-2.1-mini' | 'gpt-realtime-2025-08-28' | 'gpt-4o-realtime-preview' | 'gpt-4o-realtime-preview-2024-10-01' | 'gpt-4o-realtime-preview-2024-12-17' | 'gpt-4o-realtime-preview-2025-06-03' | 'gpt-4o-mini-realtime-preview' | 'gpt-4o-mini-realtime-preview-2024-12-17' | 'gpt-realtime-mini' | 'gpt-realtime-mini-2025-10-06' | 'gpt-realtime-mini-2025-12-15' | 'gpt-audio-1.5' | 'gpt-audio-mini' | 'gpt-audio-mini-2025-10-06' | 'gpt-audio-mini-2025-12-15' - `instructions` string — The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. - `audio` object — Configuration for input and output audio. - `input` object - `format` union - object — The PCM audio format. Only a 24kHz sample rate is supported. - … - object — The G.711 μ-law format. - … - object — The G.711 A-law format. - … - `transcription` AudioTranscription - `model` union — The model to use for transcription. Current options are `whisper-1`, `gpt-transcribe`, `gpt-live-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. - … - `language` string — The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency. - `languages` string[] — Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format. Supported by `gpt-transcribe` and `gpt-live-transcribe`. - `keywords` string[] — Words or phrases to guide transcription of the input audio. Supported by `gpt-transcribe` and `gpt-live-transcribe`. - `prompt` string — 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](https://platform.openai.com/docs/guides/speech-to-text#prompting). For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. - `delay` 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' — Controls how long the model waits before emitting transcription text. Higher values can improve transcription accuracy at the cost of latency. Only supported with `gpt-realtime-whisper` in GA Realtime sessions. - `noise_reduction` object — Configuration for input audio noise reduction. This can be set to `null` to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. - `type` 'near_field' | 'far_field' — Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. - `turn_detection` union - object — Server-side voice activity detection (VAD) which flips on when user speech is detected and off after a period of silence. - … - object — Server-side semantic turn detection which uses a model to determine when the user has finished speaking. - … - `output` object - `format` union - object — The PCM audio format. Only a 24kHz sample rate is supported. - … - object — The G.711 μ-law format. - … - object — The G.711 A-law format. - … - `voice` union - string - 'alloy' | 'ash' | 'ballad' | 'coral' | 'echo' | 'sage' | 'shimmer' | 'verse' | 'marin' | 'cedar' - `speed` number — The speed of the model's spoken response as a multiple of the original speed. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress. This parameter is a post-processing adjustment to the audio after it is generated, it's also possible to prompt the model to speak faster or slower. - `include` string[] — Additional fields to include in server outputs. `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. - `tracing` union - 'auto' — Enables tracing and sets default values for tracing configuration options. Always `auto`. - object — Granular configuration for tracing. - `workflow_name` string — The name of the workflow to attach to this trace. This is used to name the trace in the Traces Dashboard. - `group_id` string — The group id to attach to this trace to enable filtering and grouping in the Traces Dashboard. - `metadata` object — The arbitrary metadata to attach to this trace to enable filtering in the Traces Dashboard. - `tools` union[] — Tools available to the model. - union - RealtimeFunctionTool - `type` 'function' — The type of the tool, i.e. `function`. - `name` string — The name of the function. - `description` string — The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything). - `parameters` object — Parameters of the function in JSON Schema. - MCPTool — Give the model access to additional tools via remote Model Context Protocol (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp). - `type` 'mcp', required — The type of the MCP tool. Always `mcp`. - `server_label` string, required — A label for this MCP server, used to identify it in tool calls. - `server_url` string, uri — The URL for the MCP server. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `connector_id` 'connector_dropbox' | 'connector_gmail' | 'connector_googlecalendar' | 'connector_googledrive' | 'connector_microsoftteams' | 'connector_outlookcalendar' | 'connector_outlookemail' | 'connector_sharepoint' — Identifier for service connectors, like those available in ChatGPT. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. Learn more about service connectors [here](https://platform.openai.com/docs/guides/tools-remote-mcp#connectors). Currently supported `connector_id` values are: - Dropbox: `connector_dropbox` - Gmail: `connector_gmail` - Google Calendar: `connector_googlecalendar` - Google Drive: `connector_googledrive` - Microsoft Teams: `connector_microsoftteams` - Outlook Calendar: `connector_outlookcalendar` - Outlook Email: `connector_outlookemail` - SharePoint: `connector_sharepoint` - `tunnel_id` string — The Secure MCP Tunnel ID to use instead of a direct server URL. One of `server_url`, `connector_id`, or `tunnel_id` must be provided. - `authorization` string — An OAuth access token that can be used with a remote MCP server, either with a custom MCP server URL or a service connector. Your application must handle the OAuth authorization flow and provide the token here. - `server_description` string — Optional description of the MCP server, used to provide more context. - `headers` object, nullable — Optional HTTP headers to send to the MCP server. Use for authentication or other purposes. - `allowed_tools` union - … - `allowed_callers` CallableToolAllowedCaller[], nullable — The tool invocation context(s). - `require_approval` union - … - `defer_loading` boolean — Whether this MCP tool is deferred and discovered via tool search. - `tool_choice` union — How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool. - 'none' | 'auto' | 'required' — Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. - ToolChoiceFunction — Use this option to force the model to call a specific function. - `type` 'function', required — For function calling, the type is always `function`. - `name` string, required — The name of the function to call. - ToolChoiceMCP — Use this option to force the model to call a specific tool on a remote MCP server. - `type` 'mcp', required — For MCP tools, the type is always `mcp`. - `server_label` string, required — The label of the MCP server to use. - `name` string, nullable — The name of the tool to call on the server. - `reasoning` RealtimeReasoning — Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`. - `effort` 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' — Constrains effort on reasoning for reasoning-capable Realtime models such as `gpt-realtime-2`. - `max_output_tokens` union — Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or `inf` for the maximum available tokens for a given model. Defaults to `inf`. - integer - 'inf' - `truncation` union — When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit. - 'auto' | 'disabled' — The truncation strategy to use for the session. `auto` is the default truncation strategy. `disabled` will disable truncation and emit errors when the conversation exceeds the input token limit. - object — Retain a fraction of the conversation tokens when the conversation exceeds the input token limit. This allows you to amortize truncations across multiple turns, which can help improve cached token usage. - `type` 'retention_ratio', required — Use retention ratio truncation. - `retention_ratio` number, required — Fraction of post-instruction conversation tokens to retain (`0.0` - `1.0`) when the conversation exceeds the input token limit. Setting this to `0.8` means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates. - `token_limits` object — Optional custom token limits for this truncation strategy. If not provided, the model's default token limits will be used. - `post_instructions` integer — Maximum tokens allowed in the conversation after instructions (which including tool definitions). For example, setting this to 5,000 would mean that truncation would occur when the conversation exceeds 5,000 tokens after instructions. This cannot be higher than the model's context window size minus the maximum output tokens. - `prompt` Prompt, nullable — Reference to a prompt template and its variables. [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts). - `id` string, required — The unique identifier of the prompt template to use. - `version` string, nullable — Optional version of the prompt template. - `variables` ResponsePromptVariables, nullable — Optional map of values to substitute in for variables in your prompt. The substitution values can either be strings, or other Response input types like images or files. - RealtimeTranscriptionSessionCreateResponseGA — A Realtime transcription session configuration object. - `type` 'transcription', required — The type of session. Always `transcription` for transcription sessions. - `id` string, required — Unique identifier for the session that looks like `sess_1234567890abcdef`. - `object` string, required — The object type. Always `realtime.transcription_session`. - `expires_at` integer — Expiration timestamp for the session, in seconds since epoch. - `include` string[] — Additional fields to include in server outputs. - `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription. - `audio` object — Configuration for input audio for the session. - `input` object - `format` union - object — The PCM audio format. Only a 24kHz sample rate is supported. - … - object — The G.711 μ-law format. - … - object — The G.711 A-law format. - … - `transcription` AudioTranscription - `model` union — The model to use for transcription. Current options are `whisper-1`, `gpt-transcribe`, `gpt-live-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels. - … - `language` string — The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency. - `languages` string[] — Possible languages of the input audio, in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format. Supported by `gpt-transcribe` and `gpt-live-transcribe`. - `keywords` string[] — Words or phrases to guide transcription of the input audio. Supported by `gpt-transcribe` and `gpt-live-transcribe`. - `prompt` string — 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](https://platform.openai.com/docs/guides/speech-to-text#prompting). For `gpt-4o-transcribe` models (excluding `gpt-4o-transcribe-diarize`), the prompt is a free text string, for example "expect words related to technology". Prompt is not supported with `gpt-realtime-whisper` in GA Realtime sessions. - `delay` 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' — Controls how long the model waits before emitting transcription text. Higher values can improve transcription accuracy at the cost of latency. Only supported with `gpt-realtime-whisper` in GA Realtime sessions. - `noise_reduction` object — Configuration for input audio noise reduction. - `type` 'near_field' | 'far_field' — Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. - `turn_detection` object, nullable — Configuration for turn detection. Can be set to `null` to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. For `gpt-realtime-whisper`, this must be `null`; VAD is not supported. - `type` string — Type of turn detection, only `server_vad` is currently supported. - `threshold` number — Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments. - `prefix_padding_ms` integer — Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms. - `silence_duration_ms` integer — Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user. --- [API](https://skmtc.net/openai/apis/openai-api.md) · [All operations](https://skmtc.net/openai/apis/openai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/openai/openai-api/versions/dcd35773a322/schema)