@depup/openai 6.31.0-depup.0

package/resources/audio/transcriptions.d.mts.map

@@ -0,0 +1 @@
+{"version":3,"file":"transcriptions.d.mts","sourceRoot":"","sources":["../../src/resources/audio/transcriptions.ts"],"names":[],"mappings":"OAEO,EAAE,WAAW,EAAE;OACf,KAAK,iBAAiB;OACtB,KAAK,QAAQ;OACb,EAAE,UAAU,EAAE;OACd,EAAE,MAAM,EAAE;OACV,EAAE,KAAK,UAAU,EAAE;OACnB,EAAE,cAAc,EAAE;AAGzB;;GAEG;AACH,qBAAa,cAAe,SAAQ,WAAW;IAC7C;;;;;;;;;;;;;;OAcG;IACH,MAAM,CACJ,IAAI,EAAE,qCAAqC,CAAC,MAAM,GAAG,SAAS,CAAC,EAC/D,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CAAC,aAAa,CAAC;IAC5B,MAAM,CACJ,IAAI,EAAE,qCAAqC,CAAC,cAAc,CAAC,EAC3D,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CAAC,oBAAoB,CAAC;IACnC,MAAM,CACJ,IAAI,EAAE,qCAAqC,CAAC,KAAK,GAAG,KAAK,GAAG,MAAM,CAAC,EACnE,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CAAC,MAAM,CAAC;IACrB,MAAM,CAAC,IAAI,EAAE,qCAAqC,EAAE,OAAO,CAAC,EAAE,cAAc,GAAG,UAAU,CAAC,aAAa,CAAC;IACxG,MAAM,CACJ,IAAI,EAAE,kCAAkC,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CAAC,MAAM,CAAC,wBAAwB,CAAC,CAAC;IAC/C,MAAM,CACJ,IAAI,EAAE,kCAAkC,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CAAC,2BAA2B,GAAG,MAAM,GAAG,MAAM,CAAC,wBAAwB,CAAC,CAAC;CAkBvF;AAED;;;GAGG;AACH,MAAM,WAAW,aAAa;IAC5B;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;;;OAIG;IACH,QAAQ,CAAC,EAAE,KAAK,CAAC,aAAa,CAAC,OAAO,CAAC,CAAC;IAExC;;OAEG;IACH,KAAK,CAAC,EAAE,aAAa,CAAC,MAAM,GAAG,aAAa,CAAC,QAAQ,CAAC;CACvD;AAED,yBAAiB,aAAa,CAAC;IAC7B,UAAiB,OAAO;QACtB;;WAEG;QACH,KAAK,CAAC,EAAE,MAAM,CAAC;QAEf;;WAEG;QACH,KAAK,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;QAEtB;;WAEG;QACH,OAAO,CAAC,EAAE,MAAM,CAAC;KAClB;IAED;;OAEG;IACH,UAAiB,MAAM;QACrB;;WAEG;QACH,YAAY,EAAE,MAAM,CAAC;QAErB;;WAEG;QACH,aAAa,EAAE,MAAM,CAAC;QAEtB;;WAEG;QACH,YAAY,EAAE,MAAM,CAAC;QAErB;;WAEG;QACH,IAAI,EAAE,QAAQ,CAAC;QAEf;;WAEG;QACH,mBAAmB,CAAC,EAAE,MAAM,CAAC,iBAAiB,CAAC;KAChD;IAED,UAAiB,MAAM,CAAC;QACtB;;WAEG;QACH,UAAiB,iBAAiB;YAChC;;eAEG;YACH,YAAY,CAAC,EAAE,MAAM,CAAC;YAEtB;;eAEG;YACH,WAAW,CAAC,EAAE,MAAM,CAAC;SACtB;KACF;IAED;;OAEG;IACH,UAAiB,QAAQ;QACvB;;WAEG;QACH,OAAO,EAAE,MAAM,CAAC;QAEhB;;WAEG;QACH,IAAI,EAAE,UAAU,CAAC;KAClB;CACF;AAED;;;GAGG;AACH,MAAM,WAAW,qBAAqB;IACpC;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IAEjB;;OAEG;IACH,QAAQ,EAAE,KAAK,CAAC,4BAA4B,CAAC,CAAC;IAE9C;;OAEG;IACH,IAAI,EAAE,YAAY,CAAC;IAEnB;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;OAEG;IACH,KAAK,CAAC,EAAE,qBAAqB,CAAC,MAAM,GAAG,qBAAqB,CAAC,QAAQ,CAAC;CACvE;AAED,yBAAiB,qBAAqB,CAAC;IACrC;;OAEG;IACH,UAAiB,MAAM;QACrB;;WAEG;QACH,YAAY,EAAE,MAAM,CAAC;QAErB;;WAEG;QACH,aAAa,EAAE,MAAM,CAAC;QAEtB;;WAEG;QACH,YAAY,EAAE,MAAM,CAAC;QAErB;;WAEG;QACH,IAAI,EAAE,QAAQ,CAAC;QAEf;;WAEG;QACH,mBAAmB,CAAC,EAAE,MAAM,CAAC,iBAAiB,CAAC;KAChD;IAED,UAAiB,MAAM,CAAC;QACtB;;WAEG;QACH,UAAiB,iBAAiB;YAChC;;eAEG;YACH,YAAY,CAAC,EAAE,MAAM,CAAC;YAEtB;;eAEG;YACH,WAAW,CAAC,EAAE,MAAM,CAAC;SACtB;KACF;IAED;;OAEG;IACH,UAAiB,QAAQ;QACvB;;WAEG;QACH,OAAO,EAAE,MAAM,CAAC;QAEhB;;WAEG;QACH,IAAI,EAAE,UAAU,CAAC;KAClB;CACF;AAED;;GAEG;AACH,MAAM,WAAW,4BAA4B;IAC3C;;OAEG;IACH,EAAE,EAAE,MAAM,CAAC;IAEX;;OAEG;IACH,GAAG,EAAE,MAAM,CAAC;IAEZ;;;;OAIG;IACH,OAAO,EAAE,MAAM,CAAC;IAEhB;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IAEd;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;OAEG;IACH,IAAI,EAAE,yBAAyB,CAAC;CACjC;AAED,MAAM,MAAM,oBAAoB,GAAG,UAAU,CAAC;AAE9C,MAAM,WAAW,oBAAoB;IACnC;;OAEG;IACH,EAAE,EAAE,MAAM,CAAC;IAEX;;;OAGG;IACH,WAAW,EAAE,MAAM,CAAC;IAEpB;;;OAGG;IACH,iBAAiB,EAAE,MAAM,CAAC;IAE1B;;OAEG;IACH,GAAG,EAAE,MAAM,CAAC;IAEZ;;;OAGG;IACH,cAAc,EAAE,MAAM,CAAC;IAEvB;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IAEd;;OAEG;IACH,WAAW,EAAE,MAAM,CAAC;IAEpB;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;OAEG;IACH,MAAM,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;CACvB;AAED;;;;;GAKG;AACH,MAAM,MAAM,wBAAwB,GAChC,6BAA6B,GAC7B,2BAA2B,GAC3B,0BAA0B,CAAC;AAE/B;;;;;GAKG;AACH,MAAM,WAAW,2BAA2B;IAC1C;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IAEd;;OAEG;IACH,IAAI,EAAE,uBAAuB,CAAC;IAE9B;;;;OAIG;IACH,QAAQ,CAAC,EAAE,KAAK,CAAC,2BAA2B,CAAC,OAAO,CAAC,CAAC;IAEtD;;;OAGG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;CACrB;AAED,yBAAiB,2BAA2B,CAAC;IAC3C,UAAiB,OAAO;QACtB;;WAEG;QACH,KAAK,CAAC,EAAE,MAAM,CAAC;QAEf;;WAEG;QACH,KAAK,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;QAEtB;;WAEG;QACH,OAAO,CAAC,EAAE,MAAM,CAAC;KAClB;CACF;AAED;;;;;GAKG;AACH,MAAM,WAAW,0BAA0B;IACzC;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;OAEG;IACH,IAAI,EAAE,sBAAsB,CAAC;IAE7B;;;;;OAKG;IACH,QAAQ,CAAC,EAAE,KAAK,CAAC,0BAA0B,CAAC,OAAO,CAAC,CAAC;IAErD;;OAEG;IACH,KAAK,CAAC,EAAE,0BAA0B,CAAC,KAAK,CAAC;CAC1C;AAED,yBAAiB,0BAA0B,CAAC;IAC1C,UAAiB,OAAO;QACtB;;WAEG;QACH,KAAK,CAAC,EAAE,MAAM,CAAC;QAEf;;WAEG;QACH,KAAK,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;QAEtB;;WAEG;QACH,OAAO,CAAC,EAAE,MAAM,CAAC;KAClB;IAED;;OAEG;IACH,UAAiB,KAAK;QACpB;;WAEG;QACH,YAAY,EAAE,MAAM,CAAC;QAErB;;WAEG;QACH,aAAa,EAAE,MAAM,CAAC;QAEtB;;WAEG;QACH,YAAY,EAAE,MAAM,CAAC;QAErB;;WAEG;QACH,IAAI,EAAE,QAAQ,CAAC;QAEf;;WAEG;QACH,mBAAmB,CAAC,EAAE,KAAK,CAAC,iBAAiB,CAAC;KAC/C;IAED,UAAiB,KAAK,CAAC;QACrB;;WAEG;QACH,UAAiB,iBAAiB;YAChC;;eAEG;YACH,YAAY,CAAC,EAAE,MAAM,CAAC;YAEtB;;eAEG;YACH,WAAW,CAAC,EAAE,MAAM,CAAC;SACtB;KACF;CACF;AAED;;;;;GAKG;AACH,MAAM,WAAW,6BAA6B;IAC5C;;OAEG;IACH,EAAE,EAAE,MAAM,CAAC;IAEX;;OAEG;IACH,GAAG,EAAE,MAAM,CAAC;IAEZ;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAEhB;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IAEd;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;OAEG;IACH,IAAI,EAAE,yBAAyB,CAAC;CACjC;AAED;;;GAGG;AACH,MAAM,WAAW,oBAAoB;IACnC;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IAEjB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IAEjB;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IAEb;;OAEG;IACH,QAAQ,CAAC,EAAE,KAAK,CAAC,oBAAoB,CAAC,CAAC;IAEvC;;OAEG;IACH,KAAK,CAAC,EAAE,oBAAoB,CAAC,KAAK,CAAC;IAEnC;;OAEG;IACH,KAAK,CAAC,EAAE,KAAK,CAAC,iBAAiB,CAAC,CAAC;CAClC;AAED,yBAAiB,oBAAoB,CAAC;IACpC;;OAEG;IACH,UAAiB,KAAK;QACpB;;WAEG;QACH,OAAO,EAAE,MAAM,CAAC;QAEhB;;WAEG;QACH,IAAI,EAAE,UAAU,CAAC;KAClB;CACF;AAED,MAAM,WAAW,iBAAiB;IAChC;;OAEG;IACH,GAAG,EAAE,MAAM,CAAC;IAEZ;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IAEd;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;CACd;AAED;;;GAGG;AACH,MAAM,MAAM,2BAA2B,GAAG,aAAa,GAAG,qBAAqB,GAAG,oBAAoB,CAAC;AAEvG,MAAM,MAAM,yBAAyB,CACnC,cAAc,SAAS,QAAQ,CAAC,mBAAmB,GAAG,SAAS,GAAG,QAAQ,CAAC,mBAAmB,GAAG,SAAS,IACxG,qCAAqC,CAAC,cAAc,CAAC,GAAG,kCAAkC,CAAC;AAE/F,MAAM,WAAW,6BAA6B,CAC5C,cAAc,SAAS,QAAQ,CAAC,mBAAmB,GAAG,SAAS,GAAG,QAAQ,CAAC,mBAAmB,GAAG,SAAS;IAE1G;;;OAGG;IACH,IAAI,EAAE,UAAU,CAAC;IAEjB;;;;;OAKG;IACH,KAAK,EAAE,CAAC,MAAM,GAAG,EAAE,CAAC,GAAG,QAAQ,CAAC,UAAU,CAAC;IAE3C;;;;;;;OAOG;IACH,iBAAiB,CAAC,EAAE,MAAM,GAAG,yBAAyB,CAAC,SAAS,GAAG,IAAI,CAAC;IAExE;;;;;;;OAOG;IACH,OAAO,CAAC,EAAE,KAAK,CAAC,oBAAoB,CAAC,CAAC;IAEtC;;;;OAIG;IACH,mBAAmB,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;IAEpC;;;;;;OAMG;IACH,wBAAwB,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;IAEzC;;;;OAIG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAElB;;;;;;OAMG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAEhB;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,cAAc,CAAC;IAEjC;;;;;;;;;OASG;IACH,MAAM,CAAC,EAAE,OAAO,GAAG,IAAI,CAAC;IAExB;;;;;;OAMG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IAErB;;;;;;;OAOG;IACH,uBAAuB,CAAC,EAAE,KAAK,CAAC,MAAM,GAAG,SAAS,CAAC,CAAC;CACrD;AAED,yBAAiB,yBAAyB,CAAC;IACzC,UAAiB,SAAS;QACxB;;WAEG;QACH,IAAI,EAAE,YAAY,CAAC;QAEnB;;WAEG;QACH,iBAAiB,CAAC,EAAE,MAAM,CAAC;QAE3B;;;;WAIG;QACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;QAE7B;;;;WAIG;QACH,SAAS,CAAC,EAAE,MAAM,CAAC;KACpB;IAED,KAAY,qCAAqC,GAAG,iBAAiB,CAAC,qCAAqC,CAAC;IAC5G,KAAY,kCAAkC,GAAG,iBAAiB,CAAC,kCAAkC,CAAC;CACvG;AAED,MAAM,WAAW,qCAAqC,CACpD,cAAc,SAAS,QAAQ,CAAC,mBAAmB,GAAG,SAAS,GAAG,QAAQ,CAAC,mBAAmB,GAAG,SAAS,CAC1G,SAAQ,6BAA6B,CAAC,cAAc,CAAC;IACrD;;;;;;;;;OASG;IACH,MAAM,CAAC,EAAE,KAAK,GAAG,IAAI,CAAC;CACvB;AAED,MAAM,WAAW,kCAAmC,SAAQ,6BAA6B;IACvF;;;;;;;;;OASG;IACH,MAAM,EAAE,IAAI,CAAC;CACd;AAED,MAAM,CAAC,OAAO,WAAW,cAAc,CAAC;IACtC,OAAO,EACL,KAAK,aAAa,IAAI,aAAa,EACnC,KAAK,qBAAqB,IAAI,qBAAqB,EACnD,KAAK,4BAA4B,IAAI,4BAA4B,EACjE,KAAK,oBAAoB,IAAI,oBAAoB,EACjD,KAAK,oBAAoB,IAAI,oBAAoB,EACjD,KAAK,wBAAwB,IAAI,wBAAwB,EACzD,KAAK,2BAA2B,IAAI,2BAA2B,EAC/D,KAAK,0BAA0B,IAAI,0BAA0B,EAC7D,KAAK,6BAA6B,IAAI,6BAA6B,EACnE,KAAK,oBAAoB,IAAI,oBAAoB,EACjD,KAAK,iBAAiB,IAAI,iBAAiB,EAC3C,KAAK,2BAA2B,IAAI,2BAA2B,EAC/D,KAAK,yBAAyB,IAAI,yBAAyB,EAC3D,KAAK,qCAAqC,IAAI,qCAAqC,EACnF,KAAK,kCAAkC,IAAI,kCAAkC,GAC9E,CAAC;CACH"}

package/resources/audio/transcriptions.d.ts

@@ -0,0 +1,662 @@
+import { APIResource } from "../../core/resource.js";
+import * as TranscriptionsAPI from "./transcriptions.js";
+import * as AudioAPI from "./audio.js";
+import { APIPromise } from "../../core/api-promise.js";
+import { Stream } from "../../core/streaming.js";
+import { type Uploadable } from "../../core/uploads.js";
+import { RequestOptions } from "../../internal/request-options.js";
+/**
+ * Turn audio into text or text into audio.
+ */
+export declare class Transcriptions extends APIResource {
+    /**
+     * Transcribes audio into the input language.
+     *
+     * Returns a transcription object in `json`, `diarized_json`, or `verbose_json`
+     * format, or a stream of transcript events.
+     *
+     * @example
+     * ```ts
+     * const transcription =
+     *   await client.audio.transcriptions.create({
+     *     file: fs.createReadStream('speech.mp3'),
+     *     model: 'gpt-4o-transcribe',
+     *   });
+     * ```
+     */
+    create(body: TranscriptionCreateParamsNonStreaming<'json' | undefined>, options?: RequestOptions): APIPromise<Transcription>;
+    create(body: TranscriptionCreateParamsNonStreaming<'verbose_json'>, options?: RequestOptions): APIPromise<TranscriptionVerbose>;
+    create(body: TranscriptionCreateParamsNonStreaming<'srt' | 'vtt' | 'text'>, options?: RequestOptions): APIPromise<string>;
+    create(body: TranscriptionCreateParamsNonStreaming, options?: RequestOptions): APIPromise<Transcription>;
+    create(body: TranscriptionCreateParamsStreaming, options?: RequestOptions): APIPromise<Stream<TranscriptionStreamEvent>>;
+    create(body: TranscriptionCreateParamsStreaming, options?: RequestOptions): APIPromise<TranscriptionCreateResponse | string | Stream<TranscriptionStreamEvent>>;
+}
+/**
+ * Represents a transcription response returned by model, based on the provided
+ * input.
+ */
+export interface Transcription {
+    /**
+     * The transcribed text.
+     */
+    text: string;
+    /**
+     * The log probabilities of the tokens in the transcription. Only returned with the
+     * models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added
+     * to the `include` array.
+     */
+    logprobs?: Array<Transcription.Logprob>;
+    /**
+     * Token usage statistics for the request.
+     */
+    usage?: Transcription.Tokens | Transcription.Duration;
+}
+export declare namespace Transcription {
+    interface Logprob {
+        /**
+         * The token in the transcription.
+         */
+        token?: string;
+        /**
+         * The bytes of the token.
+         */
+        bytes?: Array<number>;
+        /**
+         * The log probability of the token.
+         */
+        logprob?: number;
+    }
+    /**
+     * Usage statistics for models billed by token usage.
+     */
+    interface Tokens {
+        /**
+         * Number of input tokens billed for this request.
+         */
+        input_tokens: number;
+        /**
+         * Number of output tokens generated.
+         */
+        output_tokens: number;
+        /**
+         * Total number of tokens used (input + output).
+         */
+        total_tokens: number;
+        /**
+         * The type of the usage object. Always `tokens` for this variant.
+         */
+        type: 'tokens';
+        /**
+         * Details about the input tokens billed for this request.
+         */
+        input_token_details?: Tokens.InputTokenDetails;
+    }
+    namespace Tokens {
+        /**
+         * Details about the input tokens billed for this request.
+         */
+        interface InputTokenDetails {
+            /**
+             * Number of audio tokens billed for this request.
+             */
+            audio_tokens?: number;
+            /**
+             * Number of text tokens billed for this request.
+             */
+            text_tokens?: number;
+        }
+    }
+    /**
+     * Usage statistics for models billed by audio input duration.
+     */
+    interface Duration {
+        /**
+         * Duration of the input audio in seconds.
+         */
+        seconds: number;
+        /**
+         * The type of the usage object. Always `duration` for this variant.
+         */
+        type: 'duration';
+    }
+}
+/**
+ * Represents a diarized transcription response returned by the model, including
+ * the combined transcript and speaker-segment annotations.
+ */
+export interface TranscriptionDiarized {
+    /**
+     * Duration of the input audio in seconds.
+     */
+    duration: number;
+    /**
+     * Segments of the transcript annotated with timestamps and speaker labels.
+     */
+    segments: Array<TranscriptionDiarizedSegment>;
+    /**
+     * The type of task that was run. Always `transcribe`.
+     */
+    task: 'transcribe';
+    /**
+     * The concatenated transcript text for the entire audio input.
+     */
+    text: string;
+    /**
+     * Token or duration usage statistics for the request.
+     */
+    usage?: TranscriptionDiarized.Tokens | TranscriptionDiarized.Duration;
+}
+export declare namespace TranscriptionDiarized {
+    /**
+     * Usage statistics for models billed by token usage.
+     */
+    interface Tokens {
+        /**
+         * Number of input tokens billed for this request.
+         */
+        input_tokens: number;
+        /**
+         * Number of output tokens generated.
+         */
+        output_tokens: number;
+        /**
+         * Total number of tokens used (input + output).
+         */
+        total_tokens: number;
+        /**
+         * The type of the usage object. Always `tokens` for this variant.
+         */
+        type: 'tokens';
+        /**
+         * Details about the input tokens billed for this request.
+         */
+        input_token_details?: Tokens.InputTokenDetails;
+    }
+    namespace Tokens {
+        /**
+         * Details about the input tokens billed for this request.
+         */
+        interface InputTokenDetails {
+            /**
+             * Number of audio tokens billed for this request.
+             */
+            audio_tokens?: number;
+            /**
+             * Number of text tokens billed for this request.
+             */
+            text_tokens?: number;
+        }
+    }
+    /**
+     * Usage statistics for models billed by audio input duration.
+     */
+    interface Duration {
+        /**
+         * Duration of the input audio in seconds.
+         */
+        seconds: number;
+        /**
+         * The type of the usage object. Always `duration` for this variant.
+         */
+        type: 'duration';
+    }
+}
+/**
+ * A segment of diarized transcript text with speaker metadata.
+ */
+export interface TranscriptionDiarizedSegment {
+    /**
+     * Unique identifier for the segment.
+     */
+    id: string;
+    /**
+     * End timestamp of the segment in seconds.
+     */
+    end: number;
+    /**
+     * Speaker label for this segment. When known speakers are provided, the label
+     * matches `known_speaker_names[]`. Otherwise speakers are labeled sequentially
+     * using capital letters (`A`, `B`, ...).
+     */
+    speaker: string;
+    /**
+     * Start timestamp of the segment in seconds.
+     */
+    start: number;
+    /**
+     * Transcript text for this segment.
+     */
+    text: string;
+    /**
+     * The type of the segment. Always `transcript.text.segment`.
+     */
+    type: 'transcript.text.segment';
+}
+export type TranscriptionInclude = 'logprobs';
+export interface TranscriptionSegment {
+    /**
+     * Unique identifier of the segment.
+     */
+    id: number;
+    /**
+     * Average logprob of the segment. If the value is lower than -1, consider the
+     * logprobs failed.
+     */
+    avg_logprob: number;
+    /**
+     * Compression ratio of the segment. If the value is greater than 2.4, consider the
+     * compression failed.
+     */
+    compression_ratio: number;
+    /**
+     * End time of the segment in seconds.
+     */
+    end: number;
+    /**
+     * Probability of no speech in the segment. If the value is higher than 1.0 and the
+     * `avg_logprob` is below -1, consider this segment silent.
+     */
+    no_speech_prob: number;
+    /**
+     * Seek offset of the segment.
+     */
+    seek: number;
+    /**
+     * Start time of the segment in seconds.
+     */
+    start: number;
+    /**
+     * Temperature parameter used for generating the segment.
+     */
+    temperature: number;
+    /**
+     * Text content of the segment.
+     */
+    text: string;
+    /**
+     * Array of token IDs for the text content.
+     */
+    tokens: Array<number>;
+}
+/**
+ * Emitted when a diarized transcription returns a completed segment with speaker
+ * information. Only emitted when you
+ * [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription)
+ * with `stream` set to `true` and `response_format` set to `diarized_json`.
+ */
+export type TranscriptionStreamEvent = TranscriptionTextSegmentEvent | TranscriptionTextDeltaEvent | TranscriptionTextDoneEvent;
+/**
+ * Emitted when there is an additional text delta. This is also the first event
+ * emitted when the transcription starts. Only emitted when you
+ * [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription)
+ * with the `Stream` parameter set to `true`.
+ */
+export interface TranscriptionTextDeltaEvent {
+    /**
+     * The text delta that was additionally transcribed.
+     */
+    delta: string;
+    /**
+     * The type of the event. Always `transcript.text.delta`.
+     */
+    type: 'transcript.text.delta';
+    /**
+     * The log probabilities of the delta. Only included if you
+     * [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription)
+     * with the `include[]` parameter set to `logprobs`.
+     */
+    logprobs?: Array<TranscriptionTextDeltaEvent.Logprob>;
+    /**
+     * Identifier of the diarized segment that this delta belongs to. Only present when
+     * using `gpt-4o-transcribe-diarize`.
+     */
+    segment_id?: string;
+}
+export declare namespace TranscriptionTextDeltaEvent {
+    interface Logprob {
+        /**
+         * The token that was used to generate the log probability.
+         */
+        token?: string;
+        /**
+         * The bytes that were used to generate the log probability.
+         */
+        bytes?: Array<number>;
+        /**
+         * The log probability of the token.
+         */
+        logprob?: number;
+    }
+}
+/**
+ * Emitted when the transcription is complete. Contains the complete transcription
+ * text. Only emitted when you
+ * [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription)
+ * with the `Stream` parameter set to `true`.
+ */
+export interface TranscriptionTextDoneEvent {
+    /**
+     * The text that was transcribed.
+     */
+    text: string;
+    /**
+     * The type of the event. Always `transcript.text.done`.
+     */
+    type: 'transcript.text.done';
+    /**
+     * The log probabilities of the individual tokens in the transcription. Only
+     * included if you
+     * [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription)
+     * with the `include[]` parameter set to `logprobs`.
+     */
+    logprobs?: Array<TranscriptionTextDoneEvent.Logprob>;
+    /**
+     * Usage statistics for models billed by token usage.
+     */
+    usage?: TranscriptionTextDoneEvent.Usage;
+}
+export declare namespace TranscriptionTextDoneEvent {
+    interface Logprob {
+        /**
+         * The token that was used to generate the log probability.
+         */
+        token?: string;
+        /**
+         * The bytes that were used to generate the log probability.
+         */
+        bytes?: Array<number>;
+        /**
+         * The log probability of the token.
+         */
+        logprob?: number;
+    }
+    /**
+     * Usage statistics for models billed by token usage.
+     */
+    interface Usage {
+        /**
+         * Number of input tokens billed for this request.
+         */
+        input_tokens: number;
+        /**
+         * Number of output tokens generated.
+         */
+        output_tokens: number;
+        /**
+         * Total number of tokens used (input + output).
+         */
+        total_tokens: number;
+        /**
+         * The type of the usage object. Always `tokens` for this variant.
+         */
+        type: 'tokens';
+        /**
+         * Details about the input tokens billed for this request.
+         */
+        input_token_details?: Usage.InputTokenDetails;
+    }
+    namespace Usage {
+        /**
+         * Details about the input tokens billed for this request.
+         */
+        interface InputTokenDetails {
+            /**
+             * Number of audio tokens billed for this request.
+             */
+            audio_tokens?: number;
+            /**
+             * Number of text tokens billed for this request.
+             */
+            text_tokens?: number;
+        }
+    }
+}
+/**
+ * Emitted when a diarized transcription returns a completed segment with speaker
+ * information. Only emitted when you
+ * [create a transcription](https://platform.openai.com/docs/api-reference/audio/create-transcription)
+ * with `stream` set to `true` and `response_format` set to `diarized_json`.
+ */
+export interface TranscriptionTextSegmentEvent {
+    /**
+     * Unique identifier for the segment.
+     */
+    id: string;
+    /**
+     * End timestamp of the segment in seconds.
+     */
+    end: number;
+    /**
+     * Speaker label for this segment.
+     */
+    speaker: string;
+    /**
+     * Start timestamp of the segment in seconds.
+     */
+    start: number;
+    /**
+     * Transcript text for this segment.
+     */
+    text: string;
+    /**
+     * The type of the event. Always `transcript.text.segment`.
+     */
+    type: 'transcript.text.segment';
+}
+/**
+ * Represents a verbose json transcription response returned by model, based on the
+ * provided input.
+ */
+export interface TranscriptionVerbose {
+    /**
+     * The duration of the input audio.
+     */
+    duration: number;
+    /**
+     * The language of the input audio.
+     */
+    language: string;
+    /**
+     * The transcribed text.
+     */
+    text: string;
+    /**
+     * Segments of the transcribed text and their corresponding details.
+     */
+    segments?: Array<TranscriptionSegment>;
+    /**
+     * Usage statistics for models billed by audio input duration.
+     */
+    usage?: TranscriptionVerbose.Usage;
+    /**
+     * Extracted words and their corresponding timestamps.
+     */
+    words?: Array<TranscriptionWord>;
+}
+export declare namespace TranscriptionVerbose {
+    /**
+     * Usage statistics for models billed by audio input duration.
+     */
+    interface Usage {
+        /**
+         * Duration of the input audio in seconds.
+         */
+        seconds: number;
+        /**
+         * The type of the usage object. Always `duration` for this variant.
+         */
+        type: 'duration';
+    }
+}
+export interface TranscriptionWord {
+    /**
+     * End time of the word in seconds.
+     */
+    end: number;
+    /**
+     * Start time of the word in seconds.
+     */
+    start: number;
+    /**
+     * The text content of the word.
+     */
+    word: string;
+}
+/**
+ * Represents a transcription response returned by model, based on the provided
+ * input.
+ */
+export type TranscriptionCreateResponse = Transcription | TranscriptionDiarized | TranscriptionVerbose;
+export type TranscriptionCreateParams<ResponseFormat extends AudioAPI.AudioResponseFormat | undefined = AudioAPI.AudioResponseFormat | undefined> = TranscriptionCreateParamsNonStreaming<ResponseFormat> | TranscriptionCreateParamsStreaming;
+export interface TranscriptionCreateParamsBase<ResponseFormat extends AudioAPI.AudioResponseFormat | undefined = AudioAPI.AudioResponseFormat | undefined> {
+    /**
+     * The audio file object (not file name) to transcribe, in one of these formats:
+     * flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
+     */
+    file: Uploadable;
+    /**
+     * ID of the model to use. The options are `gpt-4o-transcribe`,
+     * `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+     * (which is powered by our open source Whisper V2 model), and
+     * `gpt-4o-transcribe-diarize`.
+     */
+    model: (string & {}) | AudioAPI.AudioModel;
+    /**
+     * Controls how the audio is cut into chunks. When set to `"auto"`, the server
+     * first normalizes loudness and then uses voice activity detection (VAD) to choose
+     * boundaries. `server_vad` object can be provided to tweak VAD detection
+     * parameters manually. If unset, the audio is transcribed as a single block.
+     * Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30
+     * seconds.
+     */
+    chunking_strategy?: 'auto' | TranscriptionCreateParams.VadConfig | null;
+    /**
+     * Additional information to include in the transcription response. `logprobs` will
+     * return the log probabilities of the tokens in the response to understand the
+     * model's confidence in the transcription. `logprobs` only works with
+     * response_format set to `json` and only with the models `gpt-4o-transcribe`,
+     * `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+     * not supported when using `gpt-4o-transcribe-diarize`.
+     */
+    include?: Array<TranscriptionInclude>;
+    /**
+     * Optional list of speaker names that correspond to the audio samples provided in
+     * `known_speaker_references[]`. Each entry should be a short identifier (for
+     * example `customer` or `agent`). Up to 4 speakers are supported.
+     */
+    known_speaker_names?: Array<string>;
+    /**
+     * Optional list of audio samples (as
+     * [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+     * that contain known speaker references matching `known_speaker_names[]`. Each
+     * sample must be between 2 and 10 seconds, and can use any of the same input audio
+     * formats supported by `file`.
+     */
+    known_speaker_references?: Array<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.
+     */
+    language?: string;
+    /**
+     * An optional text to guide the model's style or continue a previous audio
+     * segment. The
+     * [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+     * should match the audio language. This field is not supported when using
+     * `gpt-4o-transcribe-diarize`.
+     */
+    prompt?: string;
+    /**
+     * The format of the output, in one of these options: `json`, `text`, `srt`,
+     * `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and
+     * `gpt-4o-mini-transcribe`, the only supported format is `json`. For
+     * `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and
+     * `diarized_json`, with `diarized_json` required to receive speaker annotations.
+     */
+    response_format?: ResponseFormat;
+    /**
+     * If set to true, the model response data will be streamed to the client as it is
+     * generated using
+     * [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+     * See the
+     * [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+     * for more information.
+     *
+     * Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+     */
+    stream?: boolean | null;
+    /**
+     * The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
+     * output more random, while lower values like 0.2 will make it more focused and
+     * deterministic. If set to 0, the model will use
+     * [log probability](https://en.wikipedia.org/wiki/Log_probability) to
+     * automatically increase the temperature until certain thresholds are hit.
+     */
+    temperature?: number;
+    /**
+     * The timestamp granularities to populate for this transcription.
+     * `response_format` must be set `verbose_json` to use timestamp granularities.
+     * Either or both of these options are supported: `word`, or `segment`. Note: There
+     * is no additional latency for segment timestamps, but generating word timestamps
+     * incurs additional latency. This option is not available for
+     * `gpt-4o-transcribe-diarize`.
+     */
+    timestamp_granularities?: Array<'word' | 'segment'>;
+}
+export declare namespace TranscriptionCreateParams {
+    interface VadConfig {
+        /**
+         * Must be set to `server_vad` to enable manual chunking using server side VAD.
+         */
+        type: 'server_vad';
+        /**
+         * Amount of audio to include before the VAD detected speech (in milliseconds).
+         */
+        prefix_padding_ms?: number;
+        /**
+         * Duration of silence to detect speech stop (in milliseconds). With shorter values
+         * the model will respond more quickly, but may jump in on short pauses from the
+         * user.
+         */
+        silence_duration_ms?: number;
+        /**
+         * Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher
+         * threshold will require louder audio to activate the model, and thus might
+         * perform better in noisy environments.
+         */
+        threshold?: number;
+    }
+    type TranscriptionCreateParamsNonStreaming = TranscriptionsAPI.TranscriptionCreateParamsNonStreaming;
+    type TranscriptionCreateParamsStreaming = TranscriptionsAPI.TranscriptionCreateParamsStreaming;
+}
+export interface TranscriptionCreateParamsNonStreaming<ResponseFormat extends AudioAPI.AudioResponseFormat | undefined = AudioAPI.AudioResponseFormat | undefined> extends TranscriptionCreateParamsBase<ResponseFormat> {
+    /**
+     * If set to true, the model response data will be streamed to the client as it is
+     * generated using
+     * [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+     * See the
+     * [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+     * for more information.
+     *
+     * Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+     */
+    stream?: false | null;
+}
+export interface TranscriptionCreateParamsStreaming extends TranscriptionCreateParamsBase {
+    /**
+     * If set to true, the model response data will be streamed to the client as it is
+     * generated using
+     * [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+     * See the
+     * [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+     * for more information.
+     *
+     * Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+     */
+    stream: true;
+}
+export declare namespace Transcriptions {
+    export { type Transcription as Transcription, type TranscriptionDiarized as TranscriptionDiarized, type TranscriptionDiarizedSegment as TranscriptionDiarizedSegment, type TranscriptionInclude as TranscriptionInclude, type TranscriptionSegment as TranscriptionSegment, type TranscriptionStreamEvent as TranscriptionStreamEvent, type TranscriptionTextDeltaEvent as TranscriptionTextDeltaEvent, type TranscriptionTextDoneEvent as TranscriptionTextDoneEvent, type TranscriptionTextSegmentEvent as TranscriptionTextSegmentEvent, type TranscriptionVerbose as TranscriptionVerbose, type TranscriptionWord as TranscriptionWord, type TranscriptionCreateResponse as TranscriptionCreateResponse, type TranscriptionCreateParams as TranscriptionCreateParams, type TranscriptionCreateParamsNonStreaming as TranscriptionCreateParamsNonStreaming, type TranscriptionCreateParamsStreaming as TranscriptionCreateParamsStreaming, };
+}
+//# sourceMappingURL=transcriptions.d.ts.map