From 7154e35221cb906b853c0271ec4badeeef7c825b Mon Sep 17 00:00:00 2001 From: "stainless-app[bot]" <142633134+stainless-app[bot]@users.noreply.github.com> Date: Tue, 11 Jun 2024 18:32:48 +0000 Subject: [PATCH] feat(api): Fix audio transcription response formats --- api.md | 6 +- src/resources/audio/audio.ts | 2 - src/resources/audio/index.ts | 14 +-- src/resources/audio/transcriptions.ts | 121 +------------------------- src/resources/audio/translations.ts | 91 +------------------ 5 files changed, 6 insertions(+), 228 deletions(-) diff --git a/api.md b/api.md index ef9ec29..8c61de6 100644 --- a/api.md +++ b/api.md @@ -60,22 +60,20 @@ Methods: Types: - Transcription -- TranscriptionCreateResponse Methods: -- client.audio.transcriptions.create({ ...params }) -> TranscriptionCreateResponse +- client.audio.transcriptions.create({ ...params }) -> Transcription ## Translations Types: - Translation -- TranslationCreateResponse Methods: -- client.audio.translations.create({ ...params }) -> TranslationCreateResponse +- client.audio.translations.create({ ...params }) -> Translation # Models diff --git a/src/resources/audio/audio.ts b/src/resources/audio/audio.ts index de125d9..97dfbe9 100644 --- a/src/resources/audio/audio.ts +++ b/src/resources/audio/audio.ts @@ -12,10 +12,8 @@ export class Audio extends APIResource { export namespace Audio { export import Transcriptions = TranscriptionsAPI.Transcriptions; export import Transcription = TranscriptionsAPI.Transcription; - export import TranscriptionCreateResponse = TranscriptionsAPI.TranscriptionCreateResponse; export import TranscriptionCreateParams = TranscriptionsAPI.TranscriptionCreateParams; export import Translations = TranslationsAPI.Translations; export import Translation = TranslationsAPI.Translation; - export import TranslationCreateResponse = TranslationsAPI.TranslationCreateResponse; export import TranslationCreateParams = TranslationsAPI.TranslationCreateParams; } diff --git a/src/resources/audio/index.ts b/src/resources/audio/index.ts index ee00487..1a2695d 100644 --- a/src/resources/audio/index.ts +++ b/src/resources/audio/index.ts @@ -1,15 +1,5 @@ // File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details. export { Audio } from './audio'; -export { - Transcription, - TranscriptionCreateResponse, - TranscriptionCreateParams, - Transcriptions, -} from './transcriptions'; -export { - Translation, - TranslationCreateResponse, - TranslationCreateParams, - Translations, -} from './translations'; +export { Transcription, TranscriptionCreateParams, Transcriptions } from './transcriptions'; +export { Translation, TranslationCreateParams, Translations } from './translations'; diff --git a/src/resources/audio/transcriptions.ts b/src/resources/audio/transcriptions.ts index 1672954..c773099 100644 --- a/src/resources/audio/transcriptions.ts +++ b/src/resources/audio/transcriptions.ts @@ -9,10 +9,7 @@ export class Transcriptions extends APIResource { /** * Transcribes audio into the input language. */ - create( - body: TranscriptionCreateParams, - options?: Core.RequestOptions, - ): Core.APIPromise { + create(body: TranscriptionCreateParams, options?: Core.RequestOptions): Core.APIPromise { return this._client.post( '/openai/v1/audio/transcriptions', multipartFormRequestOptions({ body, ...options }), @@ -31,121 +28,6 @@ export interface Transcription { text: string; } -/** - * Represents a transcription response returned by model, based on the provided - * input. - */ -export type TranscriptionCreateResponse = - | Transcription - | TranscriptionCreateResponse.CreateTranscriptionResponseVerboseJson; - -export namespace TranscriptionCreateResponse { - /** - * Represents a verbose json transcription response returned by model, based on the - * provided input. - */ - export interface CreateTranscriptionResponseVerboseJson { - /** - * The duration of the input audio. - */ - duration: string; - - /** - * The language of the input audio. - */ - language: string; - - /** - * The transcribed text. - */ - text: string; - - /** - * Segments of the transcribed text and their corresponding details. - */ - segments?: Array; - - /** - * Extracted words and their corresponding timestamps. - */ - words?: Array; - } - - export namespace CreateTranscriptionResponseVerboseJson { - export interface Segment { - /** - * 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; - } - - export interface Word { - /** - * 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; - } - } -} - export interface TranscriptionCreateParams { /** * The audio file object (not file name) to transcribe, in one of these formats: @@ -199,6 +81,5 @@ export interface TranscriptionCreateParams { export namespace Transcriptions { export import Transcription = TranscriptionsAPI.Transcription; - export import TranscriptionCreateResponse = TranscriptionsAPI.TranscriptionCreateResponse; export import TranscriptionCreateParams = TranscriptionsAPI.TranscriptionCreateParams; } diff --git a/src/resources/audio/translations.ts b/src/resources/audio/translations.ts index 179a7f2..0bd53d6 100644 --- a/src/resources/audio/translations.ts +++ b/src/resources/audio/translations.ts @@ -9,10 +9,7 @@ export class Translations extends APIResource { /** * Translates audio into English. */ - create( - body: TranslationCreateParams, - options?: Core.RequestOptions, - ): Core.APIPromise { + create(body: TranslationCreateParams, options?: Core.RequestOptions): Core.APIPromise { return this._client.post( '/openai/v1/audio/translations', multipartFormRequestOptions({ body, ...options }), @@ -24,91 +21,6 @@ export interface Translation { text: string; } -export type TranslationCreateResponse = - | Translation - | TranslationCreateResponse.CreateTranslationResponseVerboseJson; - -export namespace TranslationCreateResponse { - export interface CreateTranslationResponseVerboseJson { - /** - * The duration of the input audio. - */ - duration: string; - - /** - * The language of the output translation (always `english`). - */ - language: string; - - /** - * The translated text. - */ - text: string; - - /** - * Segments of the translated text and their corresponding details. - */ - segments?: Array; - } - - export namespace CreateTranslationResponseVerboseJson { - export interface Segment { - /** - * 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; - } - } -} - export interface TranslationCreateParams { /** * The audio file object (not file name) translate, in one of these formats: flac, @@ -146,6 +58,5 @@ export interface TranslationCreateParams { export namespace Translations { export import Translation = TranslationsAPI.Translation; - export import TranslationCreateResponse = TranslationsAPI.TranslationCreateResponse; export import TranslationCreateParams = TranslationsAPI.TranslationCreateParams; }