sambanova/resources/audio/transcriptions.d.ts

The official TypeScript library for the Samba Nova API

import { APIResource } from "../../core/resource.js";
import * as TranscriptionsAPI from "./transcriptions.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";
export declare class Transcriptions extends APIResource {
    /**
     * Transcribes audio into the input language.
     *
     * @example
     * ```ts
     * const transcription =
     *   await client.audio.transcriptions.create({
     *     file: fs.createReadStream('path/to/file'),
     *     model: 'Whisper-Large-v3',
     *   });
     * ```
     */
    create(body: TranscriptionCreateParamsNonStreaming, options?: RequestOptions): APIPromise<TranscriptionCreateResponse>;
    create(body: TranscriptionCreateParamsStreaming, options?: RequestOptions): APIPromise<Stream<TranscriptionStreamResponse>>;
    create(body: TranscriptionCreateParamsBase, options?: RequestOptions): APIPromise<Stream<TranscriptionStreamResponse> | TranscriptionCreateResponse>;
}
/**
 * Transcription response json object
 */
export interface TranscriptionResponse {
    /**
     * audio file text transcription
     */
    text: string;
    [k: string]: unknown;
}
/**
 * streamed chunk of a transcription response returned by the model
 */
export interface TranscriptionStreamResponse {
    /**
     * A unique identifier for the chat completion.
     */
    id: string;
    /**
     * A list of transcription or translation choices.
     */
    choices: Array<TranscriptionStreamResponse.Choice> | null;
    /**
     * The Unix timestamp (in seconds) of when the chat completion was created.
     */
    created: number;
    /**
     * The model used for the chat completion.
     */
    model: string;
    /**
     * The object type, always `chat.completion.chunk`.
     */
    object: 'chat.completion.chunk';
    /**
     * Backend configuration that the model runs with.
     */
    system_fingerprint: string;
    /**
     * Usage metrics for the completion, embeddings,transcription or translation
     * request
     */
    usage?: TranscriptionStreamResponse.Usage | null;
    [k: string]: unknown;
}
export declare namespace TranscriptionStreamResponse {
    /**
     * Transcription or translation chunk choice generated by streamed model responses.
     */
    interface Choice {
        /**
         * Transcription or translation response delta chunk generated by streamed model
         * responses.
         */
        delta: Choice.Delta;
        /**
         * The index of the choice in the list of choices
         */
        index: number;
        /**
         * The reason the model stopped generating tokens
         */
        finish_reason?: 'stop' | null;
        /**
         * Completion Log Probs object
         */
        logprobs?: Choice.Logprobs | null;
        [k: string]: unknown;
    }
    namespace Choice {
        /**
         * Transcription or translation response delta chunk generated by streamed model
         * responses.
         */
        interface Delta {
            /**
             * The content delta of the transcription or translation.
             */
            content: string | null;
            /**
             * The role of the messages author
             */
            role?: 'assistant' | null;
            [k: string]: unknown;
        }
        /**
         * Completion Log Probs object
         */
        interface Logprobs {
            content: Logprobs.Content;
            [k: string]: unknown;
        }
        namespace Logprobs {
            interface Content {
                token: string;
                logprob: number;
                top_logprobs: Content.TopLogprobs;
                bytes?: Array<number> | null;
                [k: string]: unknown;
            }
            namespace Content {
                interface TopLogprobs {
                    token: string;
                    logprob: number;
                    bytes?: Array<number> | null;
                    [k: string]: unknown;
                }
            }
        }
    }
    /**
     * Usage metrics for the completion, embeddings,transcription or translation
     * request
     */
    interface Usage {
        /**
         * acceptance rate
         */
        acceptance_rate?: number;
        /**
         * number of tokens generated in completion
         */
        completion_tokens?: number;
        /**
         * completion tokens per second after first token generation
         */
        completion_tokens_after_first_per_sec?: number;
        /**
         * completion tokens per second after first token generation first ten
         */
        completion_tokens_after_first_per_sec_first_ten?: number;
        /**
         * completion tokens per second after first token generation
         */
        completion_tokens_after_first_per_sec_graph?: number;
        /**
         * completion tokens per second
         */
        completion_tokens_per_sec?: number;
        /**
         * The Unix timestamp (in seconds) of when the generation finished.
         */
        end_time?: number;
        /**
         * whether or not is last response, always true for non streaming response
         */
        is_last_response?: true;
        /**
         * number of tokens used in the prompt sent
         */
        prompt_tokens?: number;
        /**
         * Extra tokens details
         */
        prompt_tokens_details?: Usage.PromptTokensDetails;
        /**
         * The Unix timestamp (in seconds) of when the generation started.
         */
        start_time?: number;
        /**
         * also TTF, time (in seconds) taken to generate the first token
         */
        time_to_first_token?: number;
        /**
         * total time (in seconds) taken to generate the full generation
         */
        total_latency?: number;
        /**
         * prompt tokens + completion tokens
         */
        total_tokens?: number;
        /**
         * tokens per second including prompt and completion
         */
        total_tokens_per_sec?: number;
        [k: string]: unknown;
    }
    namespace Usage {
        /**
         * Extra tokens details
         */
        interface PromptTokensDetails {
            /**
             * amount of cached tokens
             */
            cached_tokens?: number;
            [k: string]: unknown;
        }
    }
}
/**
 * Transcription response json object
 */
export type TranscriptionCreateResponse = TranscriptionResponse | TranscriptionStreamResponse;
export type TranscriptionCreateParams = TranscriptionCreateParamsNonStreaming | TranscriptionCreateParamsStreaming;
export interface TranscriptionCreateParamsBase {
    /**
     * The audio file object to transcribe or translate, in one of these formats: FLAC,
     * MP3, MP4, MPEG, MPGA, M4A, Ogg, WAV, or WebM format. File size limit is 25MB.
     */
    file: Uploadable;
    /**
     * The model ID to use See available
     * [models](https://docs.sambanova.ai/cloud/docs/get-started/supported-models)
     */
    model: (string & {}) | 'Whisper-Large-v3';
    /**
     * Optional language of the input audio. Supplying the input language in ISO-639-1
     * (e.g. en) format will improve accuracy and latency.
     */
    language?: 'en' | 'zh' | 'de' | 'es' | 'ru' | 'ko' | 'fr' | 'ja' | 'pt' | 'tr' | 'pl' | 'ca' | 'nl' | 'ar' | 'sv' | 'it' | 'id' | 'hi' | 'fi' | 'vi' | 'he' | 'uk' | 'el' | 'ms' | 'cs' | 'ro' | 'da' | 'hu' | 'ta' | 'no' | 'th' | 'ur' | 'hr' | 'bg' | 'lt' | 'la' | 'mi' | 'ml' | 'cy' | 'sk' | 'te' | 'fa' | 'lv' | 'bn' | 'sr' | 'az' | 'sl' | 'kn' | 'et' | 'mk' | 'br' | 'eu' | 'is' | 'hy' | 'ne' | 'mn' | 'bs' | 'kk' | 'sq' | 'sw' | 'gl' | 'mr' | 'pa' | 'si' | 'km' | 'sn' | 'yo' | 'so' | 'af' | 'oc' | 'ka' | 'be' | 'tg' | 'sd' | 'gu' | 'am' | 'yi' | 'lo' | 'uz' | 'fo' | 'ht' | 'ps' | 'tk' | 'nn' | 'mt' | 'sa' | 'lb' | 'my' | 'bo' | 'tl' | 'mg' | 'as' | 'tt' | 'haw' | 'ln' | 'ha' | 'ba' | 'jw' | 'su' | 'yue' | null;
    /**
     * Optional text prompt provided to influence transcription Translation style or
     * vocabulary. Example: “Please transcribe carefully, including pauses and
     * hesitations.”
     */
    prompt?: string | null;
    /**
     * Output format JSON or text.
     */
    response_format?: 'json' | 'text';
    /**
     * Enables streaming responses.
     */
    stream?: boolean;
    /**
     * Optional settings that apply when `stream` is true.
     */
    stream_options?: TranscriptionCreateParams.StreamOptions | null;
    [k: string]: unknown;
}
export declare namespace TranscriptionCreateParams {
    /**
     * Optional settings that apply when `stream` is true.
     */
    interface StreamOptions {
        /**
         * If true and `stream` is enabled, optional usage metadata will be included in the
         * last streamed response event.
         */
        include_usage?: boolean | null;
    }
    type TranscriptionCreateParamsNonStreaming = TranscriptionsAPI.TranscriptionCreateParamsNonStreaming;
    type TranscriptionCreateParamsStreaming = TranscriptionsAPI.TranscriptionCreateParamsStreaming;
}
export interface TranscriptionCreateParamsNonStreaming extends TranscriptionCreateParamsBase {
    /**
     * Enables streaming responses.
     */
    stream?: false;
    [k: string]: unknown;
}
export interface TranscriptionCreateParamsStreaming extends TranscriptionCreateParamsBase {
    /**
     * Enables streaming responses.
     */
    stream: true;
    [k: string]: unknown;
}
export declare namespace Transcriptions {
    export { type TranscriptionResponse as TranscriptionResponse, type TranscriptionStreamResponse as TranscriptionStreamResponse, type TranscriptionCreateResponse as TranscriptionCreateResponse, type TranscriptionCreateParams as TranscriptionCreateParams, type TranscriptionCreateParamsNonStreaming as TranscriptionCreateParamsNonStreaming, type TranscriptionCreateParamsStreaming as TranscriptionCreateParamsStreaming, };
}
//# sourceMappingURL=transcriptions.d.ts.map