openai 6.35.0 → 6.37.0

package/resources/realtime/realtime.d.mts

@@ -4,13 +4,19 @@ import * as Shared from "../shared.mjs";
 import * as CallsAPI from "./calls.mjs";
 import { CallAcceptParams, CallReferParams, CallRejectParams, Calls } from "./calls.mjs";
 import * as ClientSecretsAPI from "./client-secrets.mjs";
-import { ClientSecretCreateParams, ClientSecretCreateResponse, ClientSecrets, RealtimeSessionClientSecret, RealtimeSessionCreateResponse, RealtimeTranscriptionSessionCreateResponse, RealtimeTranscriptionSessionTurnDetection } from "./client-secrets.mjs";
+import { ClientSecretCreateParams, ClientSecretCreateResponse, ClientSecrets, RealtimeSessionCreateResponse, RealtimeTranscriptionSessionCreateResponse, RealtimeTranscriptionSessionTurnDetection } from "./client-secrets.mjs";
 import * as ResponsesAPI from "../responses/responses.mjs";
 export declare class Realtime extends APIResource {
     clientSecrets: ClientSecretsAPI.ClientSecrets;
     calls: CallsAPI.Calls;
 }
 export interface AudioTranscription {
+    /**
+     * 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.
+     */
+    delay?: 'minimal' | 'low' | 'medium' | 'high' | 'xhigh';
     /**
      * 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`)
@@ -20,16 +26,17 @@ export interface AudioTranscription {
     /**
      * The model to use for transcription. Current options are `whisper-1`,
      * `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`,
-     * `gpt-4o-transcribe`, and `gpt-4o-transcribe-diarize`. Use
-     * `gpt-4o-transcribe-diarize` when you need diarization with speaker labels.
+     * `gpt-4o-transcribe`, `gpt-4o-transcribe-diarize`, and `gpt-realtime-whisper`.
+     * Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels.
      */
-    model?: (string & {}) | 'whisper-1' | 'gpt-4o-mini-transcribe' | 'gpt-4o-mini-transcribe-2025-12-15' | 'gpt-4o-transcribe' | 'gpt-4o-transcribe-diarize';
+    model?: (string & {}) | 'whisper-1' | 'gpt-4o-mini-transcribe' | 'gpt-4o-mini-transcribe-2025-12-15' | 'gpt-4o-transcribe' | 'gpt-4o-transcribe-diarize' | 'gpt-realtime-whisper';
     /**
      * 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.
      */
     prompt?: string;
 }
@@ -1036,6 +1043,9 @@ export interface RealtimeAudioConfigInput {
      * trails off with "uhhm", the model will score a low probability of turn end and
      * wait longer for the user to continue speaking. This can be useful for more
      * natural conversations, but may have a higher latency.
+     *
+     * For `gpt-realtime-whisper` transcription sessions, turn detection must be set to
+     * `null`; VAD is not supported.
      */
     turn_detection?: RealtimeAudioInputTurnDetection | null;
 }
@@ -1143,6 +1153,9 @@ export declare namespace RealtimeAudioFormats {
  * trails off with "uhhm", the model will score a low probability of turn end and
  * wait longer for the user to continue speaking. This can be useful for more
  * natural conversations, but may have a higher latency.
+ *
+ * For `gpt-realtime-whisper` transcription sessions, turn detection must be set to
+ * `null`; VAD is not supported.
  */
 export type RealtimeAudioInputTurnDetection = RealtimeAudioInputTurnDetection.ServerVad | RealtimeAudioInputTurnDetection.SemanticVad;
 export declare namespace RealtimeAudioInputTurnDetection {
@@ -1685,6 +1698,21 @@ export interface RealtimeMcphttpError {
     message: string;
     type: 'http_error';
 }
+/**
+ * Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`.
+ */
+export interface RealtimeReasoning {
+    /**
+     * Constrains effort on reasoning for reasoning-capable Realtime models such as
+     * `gpt-realtime-2`.
+     */
+    effort?: RealtimeReasoningEffort;
+}
+/**
+ * Constrains effort on reasoning for reasoning-capable Realtime models such as
+ * `gpt-realtime-2`.
+ */
+export type RealtimeReasoningEffort = 'minimal' | 'low' | 'medium' | 'high' | 'xhigh';
 /**
  * The response resource.
  */
@@ -2000,11 +2028,20 @@ export interface RealtimeResponseCreateParams {
      * model.
      */
     output_modalities?: Array<'text' | 'audio'>;
+    /**
+     * Whether the model may call multiple tools in parallel. Only supported by
+     * reasoning Realtime models such as `gpt-realtime-2`.
+     */
+    parallel_tool_calls?: boolean;
     /**
      * Reference to a prompt template and its variables.
      * [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts).
      */
     prompt?: ResponsesAPI.ResponsePrompt | null;
+    /**
+     * Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`.
+     */
+    reasoning?: RealtimeReasoning;
     /**
      * How the model chooses tools. Provide one of the string modes or force a specific
      * function/MCP tool.
@@ -2366,6 +2403,9 @@ export interface RealtimeSession {
      * trails off with "uhhm", the model will score a low probability of turn end and
      * wait longer for the user to continue speaking. This can be useful for more
      * natural conversations, but may have a higher latency.
+     *
+     * For `gpt-realtime-whisper` transcription sessions, turn detection must be set to
+     * `null`; VAD is not supported.
      */
     turn_detection?: RealtimeSession.ServerVad | RealtimeSession.SemanticVad | null;
     /**
@@ -2543,7 +2583,7 @@ export interface RealtimeSessionCreateRequest {
     /**
      * The Realtime model used for this session.
      */
-    model?: (string & {}) | 'gpt-realtime' | 'gpt-realtime-1.5' | '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';
+    model?: (string & {}) | 'gpt-realtime' | 'gpt-realtime-1.5' | 'gpt-realtime-2' | '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';
     /**
      * 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"]`
@@ -2551,11 +2591,20 @@ export interface RealtimeSessionCreateRequest {
      * request both `text` and `audio` at the same time.
      */
     output_modalities?: Array<'text' | 'audio'>;
+    /**
+     * Whether the model may call multiple tools in parallel. Only supported by
+     * reasoning Realtime models such as `gpt-realtime-2`.
+     */
+    parallel_tool_calls?: boolean;
     /**
      * Reference to a prompt template and its variables.
      * [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts).
      */
     prompt?: ResponsesAPI.ResponsePrompt | null;
+    /**
+     * Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`.
+     */
+    reasoning?: RealtimeReasoning;
     /**
      * How the model chooses tools. Provide one of the string modes or force a specific
      * function/MCP tool.
@@ -2823,6 +2872,9 @@ export interface RealtimeTranscriptionSessionAudioInput {
      * trails off with "uhhm", the model will score a low probability of turn end and
      * wait longer for the user to continue speaking. This can be useful for more
      * natural conversations, but may have a higher latency.
+     *
+     * For `gpt-realtime-whisper` transcription sessions, turn detection must be set to
+     * `null`; VAD is not supported.
      */
     turn_detection?: RealtimeTranscriptionSessionAudioInputTurnDetection | null;
 }
@@ -2857,6 +2909,9 @@ export declare namespace RealtimeTranscriptionSessionAudioInput {
  * trails off with "uhhm", the model will score a low probability of turn end and
  * wait longer for the user to continue speaking. This can be useful for more
  * natural conversations, but may have a higher latency.
+ *
+ * For `gpt-realtime-whisper` transcription sessions, turn detection must be set to
+ * `null`; VAD is not supported.
  */
 export type RealtimeTranscriptionSessionAudioInputTurnDetection = RealtimeTranscriptionSessionAudioInputTurnDetection.ServerVad | RealtimeTranscriptionSessionAudioInputTurnDetection.SemanticVad;
 export declare namespace RealtimeTranscriptionSessionAudioInputTurnDetection {
@@ -2971,6 +3026,489 @@ export interface RealtimeTranscriptionSessionCreateRequest {
      */
     include?: Array<'item.input_audio_transcription.logprobs'>;
 }
+/**
+ * A Realtime translation client event.
+ */
+export type RealtimeTranslationClientEvent = RealtimeTranslationSessionUpdateEvent | RealtimeTranslationInputAudioBufferAppendEvent | RealtimeTranslationSessionCloseEvent;
+/**
+ * Create a translation session and client secret for the Realtime API.
+ */
+export interface RealtimeTranslationClientSecretCreateRequest {
+    /**
+     * Realtime translation session configuration. Translation sessions stream source
+     * audio in and translated audio plus transcript deltas out continuously.
+     */
+    session: RealtimeTranslationSessionCreateRequest;
+    /**
+     * 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.
+     */
+    expires_after?: RealtimeTranslationClientSecretCreateRequest.ExpiresAfter;
+}
+export declare namespace RealtimeTranslationClientSecretCreateRequest {
+    /**
+     * 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.
+     */
+    interface ExpiresAfter {
+        /**
+         * 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.
+         */
+        anchor?: 'created_at';
+        /**
+         * 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.
+         */
+        seconds?: number;
+    }
+}
+/**
+ * Response from creating a translation session and client secret for the Realtime
+ * API.
+ */
+export interface RealtimeTranslationClientSecretCreateResponse {
+    /**
+     * Expiration timestamp for the client secret, in seconds since epoch.
+     */
+    expires_at: number;
+    /**
+     * A Realtime translation session. Translation sessions continuously translate
+     * input audio into the configured output language.
+     */
+    session: RealtimeTranslationSession;
+    /**
+     * The generated client secret value.
+     */
+    value: string;
+}
+/**
+ * Send this event to append audio bytes to the translation session input audio
+ * buffer.
+ *
+ * WebSocket translation sessions accept base64-encoded 24 kHz PCM16 mono
+ * little-endian raw audio bytes. Unsupported websocket audio formats return a
+ * validation error because lower-quality audio materially degrades translation
+ * quality.
+ *
+ * Translation consumes 200 ms engine frames. For best realtime behavior, append
+ * audio in 200 ms chunks. If a chunk is shorter, the server buffers it until it
+ * has enough audio for one frame. If a chunk is longer, the server splits it into
+ * 200 ms frames and enqueues them back-to-back.
+ *
+ * Keep appending silence while the session is active. If a client stops sending
+ * audio and later resumes, model time treats the resumed audio as contiguous with
+ * the previous audio rather than as a real-world pause.
+ */
+export interface RealtimeTranslationInputAudioBufferAppendEvent {
+    /**
+     * Base64-encoded 24 kHz PCM16 mono audio bytes.
+     */
+    audio: string;
+    /**
+     * The event type, must be `session.input_audio_buffer.append`.
+     */
+    type: 'session.input_audio_buffer.append';
+    /**
+     * Optional client-generated ID used to identify this event.
+     */
+    event_id?: string;
+}
+/**
+ * Returned when optional source-language transcript text is available. This event
+ * is emitted only when `audio.input.transcription` is configured.
+ *
+ * Transcript deltas are append-only text fragments. Clients should not insert
+ * unconditional spaces between deltas.
+ */
+export interface RealtimeTranslationInputTranscriptDeltaEvent {
+    /**
+     * Append-only source-language transcript text.
+     */
+    delta: string;
+    /**
+     * The unique ID of the server event.
+     */
+    event_id: string;
+    /**
+     * The event type, must be `session.input_transcript.delta`.
+     */
+    type: 'session.input_transcript.delta';
+    /**
+     * Timing metadata for stream alignment, derived from the translation frame when
+     * available. It advances in 200 ms increments, but multiple transcript deltas may
+     * share the same `elapsed_ms`. Treat it as alignment metadata, not a unique
+     * transcript-delta identifier.
+     */
+    elapsed_ms?: number | null;
+}
+/**
+ * Returned when translated output audio is available. Output audio deltas are 200
+ * ms frames of PCM16 audio.
+ */
+export interface RealtimeTranslationOutputAudioDeltaEvent {
+    /**
+     * Base64-encoded translated audio data.
+     */
+    delta: string;
+    /**
+     * The unique ID of the server event.
+     */
+    event_id: string;
+    /**
+     * The event type, must be `session.output_audio.delta`.
+     */
+    type: 'session.output_audio.delta';
+    /**
+     * Number of audio channels.
+     */
+    channels?: number;
+    /**
+     * Timing metadata for stream alignment, derived from the translation frame when
+     * available. Treat `elapsed_ms` as alignment metadata, not a unique event
+     * identifier.
+     */
+    elapsed_ms?: number | null;
+    /**
+     * Audio encoding for `delta`.
+     */
+    format?: 'pcm16';
+    /**
+     * Sample rate of the audio delta.
+     */
+    sample_rate?: number;
+}
+/**
+ * Returned when translated transcript text is available.
+ *
+ * Transcript deltas are append-only text fragments. Clients should not insert
+ * unconditional spaces between deltas.
+ */
+export interface RealtimeTranslationOutputTranscriptDeltaEvent {
+    /**
+     * Append-only transcript text for the translated output audio.
+     */
+    delta: string;
+    /**
+     * The unique ID of the server event.
+     */
+    event_id: string;
+    /**
+     * The event type, must be `session.output_transcript.delta`.
+     */
+    type: 'session.output_transcript.delta';
+    /**
+     * Timing metadata for stream alignment, derived from the translation frame when
+     * available. It advances in 200 ms increments, but multiple transcript deltas may
+     * share the same `elapsed_ms`. Treat it as alignment metadata, not a unique
+     * transcript-delta identifier.
+     */
+    elapsed_ms?: number | null;
+}
+/**
+ * A Realtime translation server event.
+ */
+export type RealtimeTranslationServerEvent = RealtimeErrorEvent | RealtimeTranslationSessionCreatedEvent | RealtimeTranslationSessionUpdatedEvent | RealtimeTranslationSessionClosedEvent | RealtimeTranslationInputTranscriptDeltaEvent | RealtimeTranslationOutputTranscriptDeltaEvent | RealtimeTranslationOutputAudioDeltaEvent;
+/**
+ * A Realtime translation session. Translation sessions continuously translate
+ * input audio into the configured output language.
+ */
+export interface RealtimeTranslationSession {
+    /**
+     * Unique identifier for the session that looks like `sess_1234567890abcdef`.
+     */
+    id: string;
+    /**
+     * Configuration for translation input and output audio.
+     */
+    audio: RealtimeTranslationSession.Audio;
+    /**
+     * Expiration timestamp for the session, in seconds since epoch.
+     */
+    expires_at: number;
+    /**
+     * The Realtime translation model used for this session. This field is set at
+     * session creation and cannot be changed with `session.update`.
+     */
+    model: string;
+    /**
+     * The session type. Always `translation` for Realtime translation sessions.
+     */
+    type: 'translation';
+}
+export declare namespace RealtimeTranslationSession {
+    /**
+     * Configuration for translation input and output audio.
+     */
+    interface Audio {
+        input?: Audio.Input;
+        output?: Audio.Output;
+    }
+    namespace Audio {
+        interface Input {
+            /**
+             * Optional input noise reduction.
+             */
+            noise_reduction?: Input.NoiseReduction | null;
+            /**
+             * Optional source-language transcription. When configured, the server emits
+             * `session.input_transcript.delta` events. Translation itself still runs from the
+             * input audio stream.
+             */
+            transcription?: Input.Transcription | null;
+        }
+        namespace Input {
+            /**
+             * Optional input noise reduction.
+             */
+            interface NoiseReduction {
+                /**
+                 * 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.
+                 */
+                type: RealtimeAPI.NoiseReductionType;
+            }
+            /**
+             * Optional source-language transcription. When configured, the server emits
+             * `session.input_transcript.delta` events. Translation itself still runs from the
+             * input audio stream.
+             */
+            interface Transcription {
+                /**
+                 * The transcription model used for source transcript deltas.
+                 */
+                model: string;
+            }
+        }
+        interface Output {
+            /**
+             * Target language for translated output audio and transcript deltas.
+             */
+            language?: string;
+        }
+    }
+}
+/**
+ * Gracefully close the realtime translation session. The server flushes pending
+ * input audio and emits any remaining translated output before closing the
+ * session.
+ */
+export interface RealtimeTranslationSessionCloseEvent {
+    /**
+     * The event type, must be `session.close`.
+     */
+    type: 'session.close';
+    /**
+     * Optional client-generated ID used to identify this event.
+     */
+    event_id?: string;
+}
+/**
+ * Returned when a realtime translation session is closed.
+ */
+export interface RealtimeTranslationSessionClosedEvent {
+    /**
+     * The unique ID of the server event.
+     */
+    event_id: string;
+    /**
+     * The event type, must be `session.closed`.
+     */
+    type: 'session.closed';
+}
+/**
+ * Realtime translation session configuration. Translation sessions stream source
+ * audio in and translated audio plus transcript deltas out continuously.
+ */
+export interface RealtimeTranslationSessionCreateRequest {
+    /**
+     * The Realtime translation model used for this session.
+     */
+    model: string;
+    /**
+     * Configuration for translation input and output audio.
+     */
+    audio?: RealtimeTranslationSessionCreateRequest.Audio;
+}
+export declare namespace RealtimeTranslationSessionCreateRequest {
+    /**
+     * Configuration for translation input and output audio.
+     */
+    interface Audio {
+        input?: Audio.Input;
+        output?: Audio.Output;
+    }
+    namespace Audio {
+        interface Input {
+            /**
+             * Optional input noise reduction. Set to `null` to disable it.
+             */
+            noise_reduction?: Input.NoiseReduction | null;
+            /**
+             * Optional source-language transcription. When configured, the server emits
+             * `session.input_transcript.delta` events. Translation itself still runs from the
+             * input audio stream.
+             */
+            transcription?: Input.Transcription | null;
+        }
+        namespace Input {
+            /**
+             * Optional input noise reduction. Set to `null` to disable it.
+             */
+            interface NoiseReduction {
+                /**
+                 * 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.
+                 */
+                type: RealtimeAPI.NoiseReductionType;
+            }
+            /**
+             * Optional source-language transcription. When configured, the server emits
+             * `session.input_transcript.delta` events. Translation itself still runs from the
+             * input audio stream.
+             */
+            interface Transcription {
+                /**
+                 * The transcription model to use for source transcript deltas.
+                 */
+                model: string;
+            }
+        }
+        interface Output {
+            /**
+             * Target language for translated output audio and transcript deltas.
+             */
+            language?: string;
+        }
+    }
+}
+/**
+ * Returned when a translation session is created. Emitted automatically when a new
+ * connection is established as the first server event. This event contains the
+ * default translation session configuration.
+ */
+export interface RealtimeTranslationSessionCreatedEvent {
+    /**
+     * The unique ID of the server event.
+     */
+    event_id: string;
+    /**
+     * The translation session configuration.
+     */
+    session: RealtimeTranslationSession;
+    /**
+     * The event type, must be `session.created`.
+     */
+    type: 'session.created';
+}
+/**
+ * Send this event to update the translation session configuration. Translation
+ * sessions support updates to `audio.output.language`,
+ * `audio.input.transcription`, and `audio.input.noise_reduction`.
+ */
+export interface RealtimeTranslationSessionUpdateEvent {
+    /**
+     * Translation session fields to update. The session `type` and `model` are set at
+     * creation and cannot be changed with `session.update`.
+     */
+    session: RealtimeTranslationSessionUpdateRequest;
+    /**
+     * The event type, must be `session.update`.
+     */
+    type: 'session.update';
+    /**
+     * Optional client-generated ID used to identify this event.
+     */
+    event_id?: string;
+}
+/**
+ * Realtime translation session fields that can be updated with `session.update`.
+ */
+export interface RealtimeTranslationSessionUpdateRequest {
+    /**
+     * Configuration for translation input and output audio.
+     */
+    audio?: RealtimeTranslationSessionUpdateRequest.Audio;
+}
+export declare namespace RealtimeTranslationSessionUpdateRequest {
+    /**
+     * Configuration for translation input and output audio.
+     */
+    interface Audio {
+        input?: Audio.Input;
+        output?: Audio.Output;
+    }
+    namespace Audio {
+        interface Input {
+            /**
+             * Optional input noise reduction. Set to `null` to disable it.
+             */
+            noise_reduction?: Input.NoiseReduction | null;
+            /**
+             * Optional source-language transcription. When configured, the server emits
+             * `session.input_transcript.delta` events. Translation itself still runs from the
+             * input audio stream.
+             */
+            transcription?: Input.Transcription | null;
+        }
+        namespace Input {
+            /**
+             * Optional input noise reduction. Set to `null` to disable it.
+             */
+            interface NoiseReduction {
+                /**
+                 * 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.
+                 */
+                type: RealtimeAPI.NoiseReductionType;
+            }
+            /**
+             * Optional source-language transcription. When configured, the server emits
+             * `session.input_transcript.delta` events. Translation itself still runs from the
+             * input audio stream.
+             */
+            interface Transcription {
+                /**
+                 * The transcription model to use for source transcript deltas.
+                 */
+                model: string;
+            }
+        }
+        interface Output {
+            /**
+             * Target language for translated output audio and transcript deltas.
+             */
+            language?: string;
+        }
+    }
+}
+/**
+ * Returned when a translation session is updated with a `session.update` event,
+ * unless there is an error.
+ */
+export interface RealtimeTranslationSessionUpdatedEvent {
+    /**
+     * The unique ID of the server event.
+     */
+    event_id: string;
+    /**
+     * The translation session configuration.
+     */
+    session: RealtimeTranslationSession;
+    /**
+     * The event type, must be `session.updated`.
+     */
+    type: 'session.updated';
+}
 /**
  * When the number of tokens in a conversation exceeds the model's input token
  * limit, the conversation be truncated, meaning messages (starting from the
@@ -3905,9 +4443,6 @@ export declare namespace TranscriptionSessionUpdatedEvent {
          * The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
          */
         input_audio_format?: string;
-        /**
-         * Configuration of the transcription model.
-         */
         input_audio_transcription?: RealtimeAPI.AudioTranscription;
         /**
          * The set of modalities the model can respond with. To disable audio, set this to
@@ -3970,8 +4505,8 @@ export declare namespace TranscriptionSessionUpdatedEvent {
     }
 }
 export declare namespace Realtime {
-    export { type AudioTranscription as AudioTranscription, type ConversationCreatedEvent as ConversationCreatedEvent, type ConversationItem as ConversationItem, type ConversationItemAdded as ConversationItemAdded, type ConversationItemCreateEvent as ConversationItemCreateEvent, type ConversationItemCreatedEvent as ConversationItemCreatedEvent, type ConversationItemDeleteEvent as ConversationItemDeleteEvent, type ConversationItemDeletedEvent as ConversationItemDeletedEvent, type ConversationItemDone as ConversationItemDone, type ConversationItemInputAudioTranscriptionCompletedEvent as ConversationItemInputAudioTranscriptionCompletedEvent, type ConversationItemInputAudioTranscriptionDeltaEvent as ConversationItemInputAudioTranscriptionDeltaEvent, type ConversationItemInputAudioTranscriptionFailedEvent as ConversationItemInputAudioTranscriptionFailedEvent, type ConversationItemInputAudioTranscriptionSegment as ConversationItemInputAudioTranscriptionSegment, type ConversationItemRetrieveEvent as ConversationItemRetrieveEvent, type ConversationItemTruncateEvent as ConversationItemTruncateEvent, type ConversationItemTruncatedEvent as ConversationItemTruncatedEvent, type ConversationItemWithReference as ConversationItemWithReference, type InputAudioBufferAppendEvent as InputAudioBufferAppendEvent, type InputAudioBufferClearEvent as InputAudioBufferClearEvent, type InputAudioBufferClearedEvent as InputAudioBufferClearedEvent, type InputAudioBufferCommitEvent as InputAudioBufferCommitEvent, type InputAudioBufferCommittedEvent as InputAudioBufferCommittedEvent, type InputAudioBufferDtmfEventReceivedEvent as InputAudioBufferDtmfEventReceivedEvent, type InputAudioBufferSpeechStartedEvent as InputAudioBufferSpeechStartedEvent, type InputAudioBufferSpeechStoppedEvent as InputAudioBufferSpeechStoppedEvent, type InputAudioBufferTimeoutTriggered as InputAudioBufferTimeoutTriggered, type LogProbProperties as LogProbProperties, type McpListToolsCompleted as McpListToolsCompleted, type McpListToolsFailed as McpListToolsFailed, type McpListToolsInProgress as McpListToolsInProgress, type NoiseReductionType as NoiseReductionType, type OutputAudioBufferClearEvent as OutputAudioBufferClearEvent, type RateLimitsUpdatedEvent as RateLimitsUpdatedEvent, type RealtimeAudioConfig as RealtimeAudioConfig, type RealtimeAudioConfigInput as RealtimeAudioConfigInput, type RealtimeAudioConfigOutput as RealtimeAudioConfigOutput, type RealtimeAudioFormats as RealtimeAudioFormats, type RealtimeAudioInputTurnDetection as RealtimeAudioInputTurnDetection, type RealtimeClientEvent as RealtimeClientEvent, type RealtimeConversationItemAssistantMessage as RealtimeConversationItemAssistantMessage, type RealtimeConversationItemFunctionCall as RealtimeConversationItemFunctionCall, type RealtimeConversationItemFunctionCallOutput as RealtimeConversationItemFunctionCallOutput, type RealtimeConversationItemSystemMessage as RealtimeConversationItemSystemMessage, type RealtimeConversationItemUserMessage as RealtimeConversationItemUserMessage, type RealtimeError as RealtimeError, type RealtimeErrorEvent as RealtimeErrorEvent, type RealtimeFunctionTool as RealtimeFunctionTool, type RealtimeMcpApprovalRequest as RealtimeMcpApprovalRequest, type RealtimeMcpApprovalResponse as RealtimeMcpApprovalResponse, type RealtimeMcpListTools as RealtimeMcpListTools, type RealtimeMcpProtocolError as RealtimeMcpProtocolError, type RealtimeMcpToolCall as RealtimeMcpToolCall, type RealtimeMcpToolExecutionError as RealtimeMcpToolExecutionError, type RealtimeMcphttpError as RealtimeMcphttpError, type RealtimeResponse as RealtimeResponse, type RealtimeResponseCreateAudioOutput as RealtimeResponseCreateAudioOutput, type RealtimeResponseCreateMcpTool as RealtimeResponseCreateMcpTool, type RealtimeResponseCreateParams as RealtimeResponseCreateParams, type RealtimeResponseStatus as RealtimeResponseStatus, type RealtimeResponseUsage as RealtimeResponseUsage, type RealtimeResponseUsageInputTokenDetails as RealtimeResponseUsageInputTokenDetails, type RealtimeResponseUsageOutputTokenDetails as RealtimeResponseUsageOutputTokenDetails, type RealtimeServerEvent as RealtimeServerEvent, type RealtimeSession as RealtimeSession, type RealtimeSessionCreateRequest as RealtimeSessionCreateRequest, type RealtimeToolChoiceConfig as RealtimeToolChoiceConfig, type RealtimeToolsConfig as RealtimeToolsConfig, type RealtimeToolsConfigUnion as RealtimeToolsConfigUnion, type RealtimeTracingConfig as RealtimeTracingConfig, type RealtimeTranscriptionSessionAudio as RealtimeTranscriptionSessionAudio, type RealtimeTranscriptionSessionAudioInput as RealtimeTranscriptionSessionAudioInput, type RealtimeTranscriptionSessionAudioInputTurnDetection as RealtimeTranscriptionSessionAudioInputTurnDetection, type RealtimeTranscriptionSessionCreateRequest as RealtimeTranscriptionSessionCreateRequest, type RealtimeTruncation as RealtimeTruncation, type RealtimeTruncationRetentionRatio as RealtimeTruncationRetentionRatio, type ResponseAudioDeltaEvent as ResponseAudioDeltaEvent, type ResponseAudioDoneEvent as ResponseAudioDoneEvent, type ResponseAudioTranscriptDeltaEvent as ResponseAudioTranscriptDeltaEvent, type ResponseAudioTranscriptDoneEvent as ResponseAudioTranscriptDoneEvent, type ResponseCancelEvent as ResponseCancelEvent, type ResponseContentPartAddedEvent as ResponseContentPartAddedEvent, type ResponseContentPartDoneEvent as ResponseContentPartDoneEvent, type ResponseCreateEvent as ResponseCreateEvent, type ResponseCreatedEvent as ResponseCreatedEvent, type ResponseDoneEvent as ResponseDoneEvent, type ResponseFunctionCallArgumentsDeltaEvent as ResponseFunctionCallArgumentsDeltaEvent, type ResponseFunctionCallArgumentsDoneEvent as ResponseFunctionCallArgumentsDoneEvent, type ResponseMcpCallArgumentsDelta as ResponseMcpCallArgumentsDelta, type ResponseMcpCallArgumentsDone as ResponseMcpCallArgumentsDone, type ResponseMcpCallCompleted as ResponseMcpCallCompleted, type ResponseMcpCallFailed as ResponseMcpCallFailed, type ResponseMcpCallInProgress as ResponseMcpCallInProgress, type ResponseOutputItemAddedEvent as ResponseOutputItemAddedEvent, type ResponseOutputItemDoneEvent as ResponseOutputItemDoneEvent, type ResponseTextDeltaEvent as ResponseTextDeltaEvent, type ResponseTextDoneEvent as ResponseTextDoneEvent, type SessionCreatedEvent as SessionCreatedEvent, type SessionUpdateEvent as SessionUpdateEvent, type SessionUpdatedEvent as SessionUpdatedEvent, type TranscriptionSessionUpdate as TranscriptionSessionUpdate, type TranscriptionSessionUpdatedEvent as TranscriptionSessionUpdatedEvent, };
-    export { ClientSecrets as ClientSecrets, type RealtimeSessionClientSecret as RealtimeSessionClientSecret, type RealtimeSessionCreateResponse as RealtimeSessionCreateResponse, type RealtimeTranscriptionSessionCreateResponse as RealtimeTranscriptionSessionCreateResponse, type RealtimeTranscriptionSessionTurnDetection as RealtimeTranscriptionSessionTurnDetection, type ClientSecretCreateResponse as ClientSecretCreateResponse, type ClientSecretCreateParams as ClientSecretCreateParams, };
+    export { type AudioTranscription as AudioTranscription, type ConversationCreatedEvent as ConversationCreatedEvent, type ConversationItem as ConversationItem, type ConversationItemAdded as ConversationItemAdded, type ConversationItemCreateEvent as ConversationItemCreateEvent, type ConversationItemCreatedEvent as ConversationItemCreatedEvent, type ConversationItemDeleteEvent as ConversationItemDeleteEvent, type ConversationItemDeletedEvent as ConversationItemDeletedEvent, type ConversationItemDone as ConversationItemDone, type ConversationItemInputAudioTranscriptionCompletedEvent as ConversationItemInputAudioTranscriptionCompletedEvent, type ConversationItemInputAudioTranscriptionDeltaEvent as ConversationItemInputAudioTranscriptionDeltaEvent, type ConversationItemInputAudioTranscriptionFailedEvent as ConversationItemInputAudioTranscriptionFailedEvent, type ConversationItemInputAudioTranscriptionSegment as ConversationItemInputAudioTranscriptionSegment, type ConversationItemRetrieveEvent as ConversationItemRetrieveEvent, type ConversationItemTruncateEvent as ConversationItemTruncateEvent, type ConversationItemTruncatedEvent as ConversationItemTruncatedEvent, type ConversationItemWithReference as ConversationItemWithReference, type InputAudioBufferAppendEvent as InputAudioBufferAppendEvent, type InputAudioBufferClearEvent as InputAudioBufferClearEvent, type InputAudioBufferClearedEvent as InputAudioBufferClearedEvent, type InputAudioBufferCommitEvent as InputAudioBufferCommitEvent, type InputAudioBufferCommittedEvent as InputAudioBufferCommittedEvent, type InputAudioBufferDtmfEventReceivedEvent as InputAudioBufferDtmfEventReceivedEvent, type InputAudioBufferSpeechStartedEvent as InputAudioBufferSpeechStartedEvent, type InputAudioBufferSpeechStoppedEvent as InputAudioBufferSpeechStoppedEvent, type InputAudioBufferTimeoutTriggered as InputAudioBufferTimeoutTriggered, type LogProbProperties as LogProbProperties, type McpListToolsCompleted as McpListToolsCompleted, type McpListToolsFailed as McpListToolsFailed, type McpListToolsInProgress as McpListToolsInProgress, type NoiseReductionType as NoiseReductionType, type OutputAudioBufferClearEvent as OutputAudioBufferClearEvent, type RateLimitsUpdatedEvent as RateLimitsUpdatedEvent, type RealtimeAudioConfig as RealtimeAudioConfig, type RealtimeAudioConfigInput as RealtimeAudioConfigInput, type RealtimeAudioConfigOutput as RealtimeAudioConfigOutput, type RealtimeAudioFormats as RealtimeAudioFormats, type RealtimeAudioInputTurnDetection as RealtimeAudioInputTurnDetection, type RealtimeClientEvent as RealtimeClientEvent, type RealtimeConversationItemAssistantMessage as RealtimeConversationItemAssistantMessage, type RealtimeConversationItemFunctionCall as RealtimeConversationItemFunctionCall, type RealtimeConversationItemFunctionCallOutput as RealtimeConversationItemFunctionCallOutput, type RealtimeConversationItemSystemMessage as RealtimeConversationItemSystemMessage, type RealtimeConversationItemUserMessage as RealtimeConversationItemUserMessage, type RealtimeError as RealtimeError, type RealtimeErrorEvent as RealtimeErrorEvent, type RealtimeFunctionTool as RealtimeFunctionTool, type RealtimeMcpApprovalRequest as RealtimeMcpApprovalRequest, type RealtimeMcpApprovalResponse as RealtimeMcpApprovalResponse, type RealtimeMcpListTools as RealtimeMcpListTools, type RealtimeMcpProtocolError as RealtimeMcpProtocolError, type RealtimeMcpToolCall as RealtimeMcpToolCall, type RealtimeMcpToolExecutionError as RealtimeMcpToolExecutionError, type RealtimeMcphttpError as RealtimeMcphttpError, type RealtimeReasoning as RealtimeReasoning, type RealtimeReasoningEffort as RealtimeReasoningEffort, type RealtimeResponse as RealtimeResponse, type RealtimeResponseCreateAudioOutput as RealtimeResponseCreateAudioOutput, type RealtimeResponseCreateMcpTool as RealtimeResponseCreateMcpTool, type RealtimeResponseCreateParams as RealtimeResponseCreateParams, type RealtimeResponseStatus as RealtimeResponseStatus, type RealtimeResponseUsage as RealtimeResponseUsage, type RealtimeResponseUsageInputTokenDetails as RealtimeResponseUsageInputTokenDetails, type RealtimeResponseUsageOutputTokenDetails as RealtimeResponseUsageOutputTokenDetails, type RealtimeServerEvent as RealtimeServerEvent, type RealtimeSession as RealtimeSession, type RealtimeSessionCreateRequest as RealtimeSessionCreateRequest, type RealtimeToolChoiceConfig as RealtimeToolChoiceConfig, type RealtimeToolsConfig as RealtimeToolsConfig, type RealtimeToolsConfigUnion as RealtimeToolsConfigUnion, type RealtimeTracingConfig as RealtimeTracingConfig, type RealtimeTranscriptionSessionAudio as RealtimeTranscriptionSessionAudio, type RealtimeTranscriptionSessionAudioInput as RealtimeTranscriptionSessionAudioInput, type RealtimeTranscriptionSessionAudioInputTurnDetection as RealtimeTranscriptionSessionAudioInputTurnDetection, type RealtimeTranscriptionSessionCreateRequest as RealtimeTranscriptionSessionCreateRequest, type RealtimeTranslationClientEvent as RealtimeTranslationClientEvent, type RealtimeTranslationClientSecretCreateRequest as RealtimeTranslationClientSecretCreateRequest, type RealtimeTranslationClientSecretCreateResponse as RealtimeTranslationClientSecretCreateResponse, type RealtimeTranslationInputAudioBufferAppendEvent as RealtimeTranslationInputAudioBufferAppendEvent, type RealtimeTranslationInputTranscriptDeltaEvent as RealtimeTranslationInputTranscriptDeltaEvent, type RealtimeTranslationOutputAudioDeltaEvent as RealtimeTranslationOutputAudioDeltaEvent, type RealtimeTranslationOutputTranscriptDeltaEvent as RealtimeTranslationOutputTranscriptDeltaEvent, type RealtimeTranslationServerEvent as RealtimeTranslationServerEvent, type RealtimeTranslationSession as RealtimeTranslationSession, type RealtimeTranslationSessionCloseEvent as RealtimeTranslationSessionCloseEvent, type RealtimeTranslationSessionClosedEvent as RealtimeTranslationSessionClosedEvent, type RealtimeTranslationSessionCreateRequest as RealtimeTranslationSessionCreateRequest, type RealtimeTranslationSessionCreatedEvent as RealtimeTranslationSessionCreatedEvent, type RealtimeTranslationSessionUpdateEvent as RealtimeTranslationSessionUpdateEvent, type RealtimeTranslationSessionUpdateRequest as RealtimeTranslationSessionUpdateRequest, type RealtimeTranslationSessionUpdatedEvent as RealtimeTranslationSessionUpdatedEvent, type RealtimeTruncation as RealtimeTruncation, type RealtimeTruncationRetentionRatio as RealtimeTruncationRetentionRatio, type ResponseAudioDeltaEvent as ResponseAudioDeltaEvent, type ResponseAudioDoneEvent as ResponseAudioDoneEvent, type ResponseAudioTranscriptDeltaEvent as ResponseAudioTranscriptDeltaEvent, type ResponseAudioTranscriptDoneEvent as ResponseAudioTranscriptDoneEvent, type ResponseCancelEvent as ResponseCancelEvent, type ResponseContentPartAddedEvent as ResponseContentPartAddedEvent, type ResponseContentPartDoneEvent as ResponseContentPartDoneEvent, type ResponseCreateEvent as ResponseCreateEvent, type ResponseCreatedEvent as ResponseCreatedEvent, type ResponseDoneEvent as ResponseDoneEvent, type ResponseFunctionCallArgumentsDeltaEvent as ResponseFunctionCallArgumentsDeltaEvent, type ResponseFunctionCallArgumentsDoneEvent as ResponseFunctionCallArgumentsDoneEvent, type ResponseMcpCallArgumentsDelta as ResponseMcpCallArgumentsDelta, type ResponseMcpCallArgumentsDone as ResponseMcpCallArgumentsDone, type ResponseMcpCallCompleted as ResponseMcpCallCompleted, type ResponseMcpCallFailed as ResponseMcpCallFailed, type ResponseMcpCallInProgress as ResponseMcpCallInProgress, type ResponseOutputItemAddedEvent as ResponseOutputItemAddedEvent, type ResponseOutputItemDoneEvent as ResponseOutputItemDoneEvent, type ResponseTextDeltaEvent as ResponseTextDeltaEvent, type ResponseTextDoneEvent as ResponseTextDoneEvent, type SessionCreatedEvent as SessionCreatedEvent, type SessionUpdateEvent as SessionUpdateEvent, type SessionUpdatedEvent as SessionUpdatedEvent, type TranscriptionSessionUpdate as TranscriptionSessionUpdate, type TranscriptionSessionUpdatedEvent as TranscriptionSessionUpdatedEvent, };
+    export { ClientSecrets as ClientSecrets, type RealtimeSessionCreateResponse as RealtimeSessionCreateResponse, type RealtimeTranscriptionSessionCreateResponse as RealtimeTranscriptionSessionCreateResponse, type RealtimeTranscriptionSessionTurnDetection as RealtimeTranscriptionSessionTurnDetection, type ClientSecretCreateResponse as ClientSecretCreateResponse, type ClientSecretCreateParams as ClientSecretCreateParams, };
     export { Calls as Calls, type CallAcceptParams as CallAcceptParams, type CallReferParams as CallReferParams, type CallRejectParams as CallRejectParams, };
 }
 //# sourceMappingURL=realtime.d.mts.map