@deepgram/sdk 1.4.7 → 1.4.8

package/dist/types/index.d.ts

@@ -0,0 +1,38 @@
+export * from "./balance";
+export * from "./balanceList";
+export * from "./channel";
+export * from "./createKeyOptions";
+export * from "./hit";
+export * from "./invitationList";
+export * from "./invitationOptions";
+export * from "./key";
+export * from "./keyResponse";
+export * from "./liveTranscriptionOptions";
+export * from "./liveTranscriptionResponse";
+export * from "./member";
+export * from "./memberList";
+export * from "./message";
+export * from "./metadata";
+export * from "./prerecordedTranscriptionOptions";
+export * from "./prerecordedTranscriptionResponse";
+export * from "./project";
+export * from "./projectPatchResponse";
+export * from "./projectResponse";
+export * from "./scopeList";
+export * from "./search";
+export * from "./transcriptionSource";
+export * from "./usageCallback";
+export * from "./usageField";
+export * from "./usageFieldOptions";
+export * from "./usageOptions";
+export * from "./usageRequest";
+export * from "./usageRequestDetail";
+export * from "./usageRequestList";
+export * from "./usageRequestListOptions";
+export * from "./usageResponse";
+export * from "./usageResponseDetail";
+export * from "./utterance";
+export * from "./wordBase";
+export * from "./keyResponseObj";
+export * from "./projectPatchRequest";
+export * from "./requestFunction";

package/dist/types/invitationList.d.ts

@@ -0,0 +1,4 @@
+import { InvitationOptions } from "./invitationOptions";
+export declare type InvitationList = {
+    invites?: Array<InvitationOptions>;
+};

package/dist/types/invitationOptions.d.ts

@@ -0,0 +1,4 @@
+export declare type InvitationOptions = {
+    email?: string;
+    scope?: string;
+};

package/dist/types/key.d.ts

@@ -0,0 +1,25 @@
+/**
+ * API key used for authenticating with the Deepgram API
+ */
+export declare type Key = {
+    /**
+     * Unique identifier of the key to use in API requests
+     */
+    api_key_id: string;
+    /**
+     * API key to send in API requests (Only displayed when first created)
+     */
+    key?: string;
+    /**
+     * Comment for user reference
+     */
+    comment: string;
+    /**
+     * Timestamp of the date/time the key was created
+     */
+    created: string;
+    /**
+     * Array of scopes assigned to the key
+     */
+    scopes: Array<string>;
+};

package/dist/types/keyResponse.d.ts

@@ -0,0 +1,10 @@
+import { KeyResponseObj } from "./keyResponseObj";
+/**
+ * Response from the Deepgram API to list keys
+ */
+export declare type KeyResponse = {
+    /**
+     * Array of API keys associated with the project
+     */
+    api_keys: Array<KeyResponseObj>;
+};

package/dist/types/keyResponseObj.d.ts

@@ -0,0 +1,42 @@
+import { Key } from "./key";
+import { Member } from "./member";
+export declare type KeyResponseObj = {
+    /**
+     * Optional member associated with the API key
+     */
+    member?: Member;
+    /**
+     * API key
+     */
+    api_key: Key;
+    /**
+     * Unique identifier of the key to use in API requests
+     * @deprecated This property has moved to api_key.api_key_id and will
+     * be removed in future versions.
+     */
+    api_key_id: string;
+    /**
+     * API key to send in API requests (Only displayed when first created)
+     * @deprecated This property has moved to api_key.key and will
+     * be removed in future versions.
+     */
+    key?: string;
+    /**
+     * Comment for user reference
+     * @deprecated This property has moved to api_key.comment and will
+     * be removed in future versions.
+     */
+    comment: string;
+    /**
+     * Timestamp of the date/time the key was created
+     * @deprecated This property has moved to api_key.created and will
+     * be removed in future versions.
+     */
+    created: string;
+    /**
+     * Array of scopes assigned to the key
+     * @deprecated This property has moved to api_key.scopes and will
+     * be removed in future versions.
+     */
+    scopes: Array<string>;
+};

package/dist/types/keyword.d.ts

@@ -0,0 +1,4 @@
+export declare type Keyword = {
+    keyword: string;
+    boost?: number;
+};

package/dist/types/liveTranscriptionOptions.d.ts

@@ -0,0 +1,161 @@
+import { Models } from "../enums";
+/**
+ * Options for transcription
+ */
+export declare type LiveTranscriptionOptions = {
+    /**
+     * AI model used to process submitted audio.
+     * @default general
+     * @remarks Possible values are general, phonecall, meeting or a custom string
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/model
+     */
+    model?: Models | string;
+    /**
+     * Version of the model to use.
+     * @default latest
+     * @remarks latest OR <version_id>
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/version
+     */
+    version?: string;
+    /**
+     * Tier of the model to use.
+     * @default base
+     * @remarks Possible values are base or enhanced
+     * @see https://developers.deepgram.com/documentation/features/tier/
+     */
+    tier?: string;
+    /**
+     * Terms or phrases to search for in the submitted audio and replace
+     * @remarks Can send multiple instances in query string replace=this:that&replace=thisalso:thatalso. Replacing a term or phrase with nothing will remove the term or phrase from the audio transcript.
+     * @see https://developers.deepgram.com/documentation/features/replace/
+     */
+    replace?: string;
+    /**
+     * BCP-47 language tag that hints at the primary spoken language.
+     * @default en-US
+     * @remarks Possible values are en-GB, en-IN, en-NZ, en-US, es, fr, ko, pt,
+     * pt-BR, ru, tr or null
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/language
+     */
+    language?: string;
+    /**
+     * Indicates whether to add punctuation and capitalization to the transcript.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/punctuate
+     */
+    punctuate?: boolean;
+    /**
+     * Indicates whether to remove profanity from the transcript.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/profanity_filter
+     */
+    profanity_filter?: boolean;
+    /**
+     * Indicates whether to redact sensitive information, replacing redacted content with asterisks (*).
+     * @remarks Options include:
+     *  `pci`: Redacts sensitive credit card information, including credit card number, expiration date, and CVV
+     *  `numbers` (or `true)`: Aggressively redacts strings of numerals
+     *  `ssn` (*beta*): Redacts social security numbers
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/redact
+     */
+    redact?: Array<string>;
+    /**
+     * Indicates whether to recognize speaker changes. When set to true, each word
+     * in the transcript will be assigned a speaker number starting at 0.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/diarize
+     */
+    diarize?: boolean;
+    /**
+     * Indicates whether to transcribe each audio channel independently. When set
+     * to true, you will receive one transcript for each channel, which means you
+     * can apply a different model to each channel using the model parameter (e.g.,
+     * set model to general:phonecall, which applies the general model to channel
+     * 0 and the phonecall model to channel 1).
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/multichannel
+     */
+    multichannel?: boolean;
+    /**
+     * Maximum number of transcript alternatives to return. Just like a human listener,
+     * Deepgram can provide multiple possible interpretations of what it hears.
+     * @default 1
+     */
+    alternatives?: number;
+    /**
+     * Indicates whether to convert numbers from written format (e.g., one) to
+     * numerical format (e.g., 1). Deepgram can format numbers up to 999,999.
+     * @remarks Converted numbers do not include punctuation. For example,
+     * 999,999 would be transcribed as 999999.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/numerals
+     */
+    numerals?: boolean;
+    /**
+     * Terms or phrases to search for in the submitted audio. Deepgram searches
+     * for acoustic patterns in audio rather than text patterns in transcripts
+     * because we have noticed that acoustic pattern matching is more performant.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/search
+     */
+    search?: Array<string>;
+    /**
+     * Callback URL to provide if you would like your submitted audio to be
+     * processed asynchronously. When passed, Deepgram will immediately respond
+     * with a request_id. When it has finished analyzing the audio, it will send
+     * a POST request to the provided URL with an appropriate HTTP status code.
+     * @remarks You may embed basic authentication credentials in the callback URL.
+     * Only ports 80, 443, 8080, and 8443 can be used for callbacks.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/callback
+     */
+    callback?: string;
+    /**
+     * Keywords to which the model should pay particular attention to boosting
+     * or suppressing to help it understand context. Just like a human listener,
+     * Deepgram can better understand mumbled, distorted, or otherwise
+     * hard-to-decipher speech when it knows the context of the conversation.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/keywords
+     */
+    keywords?: Array<string>;
+    /**
+     * Indicates whether the streaming endpoint should send you updates to its
+     * transcription as more audio becomes available. By default, the streaming
+     * endpoint returns regular updates, which means transcription results will
+     * likely change for a period of time. You can avoid receiving these updates
+     * by setting this flag to false.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeStreamingAudio/properties/interim_results
+     */
+    interim_results?: boolean;
+    /**
+     * Indicates whether Deepgram will detect whether a speaker has finished
+     * speaking (or paused for a significant period of time, indicating the
+     * completion of an idea). When Deepgram detects an endpoint, it assumes
+     * that no additional data will improve its prediction, so it immediately
+     * finalizes the result for the processed time range and returns the
+     * transcript with a speech_final parameter set to true.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeStreamingAudio/properties/endpointing
+     */
+    endpointing?: boolean;
+    /**
+     * Length of time in milliseconds of silence that voice activation detection
+     * (VAD) will use to detect that a speaker has finished speaking. Used when
+     * endpointing is enabled. Defaults to 10 ms. Deepgram customers may configure
+     * a value between 10 ms and 500 ms; on-premise customers may remove this
+     * restriction.
+     * @default 10
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeStreamingAudio/properties/vad_turnoff
+     */
+    vad_turnoff?: number;
+    /**
+     * Expected encoding of the submitted streaming audio.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeStreamingAudio/properties/encoding
+     */
+    encoding?: string;
+    /**
+     * Number of independent audio channels contained in submitted streaming
+     * audio. Only read when a value is provided for encoding.
+     * @default 1
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeStreamingAudio/properties/channels
+     */
+    channels?: number;
+    /**
+     * Sample rate of submitted streaming audio. Required (and only read)
+     * when a value is provided for encoding.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeStreamingAudio/properties/sample_rate
+     */
+    sample_rate?: number;
+};

package/dist/types/liveTranscriptionResponse.d.ts

@@ -0,0 +1,9 @@
+import { Channel } from "./channel";
+export declare type LiveTranscriptionResponse = {
+    channel_index: Array<number>;
+    duration: number;
+    start: number;
+    is_final: boolean;
+    speech_final: boolean;
+    channel: Channel;
+};

package/dist/types/member.d.ts

@@ -0,0 +1,7 @@
+export declare type Member = {
+    member_id: string;
+    first_name?: string;
+    last_name?: string;
+    scopes?: Array<string>;
+    email: string;
+};

package/dist/types/memberList.d.ts

@@ -0,0 +1,4 @@
+import { Member } from "./member";
+export declare type MemberList = {
+    members?: Array<Member>;
+};

package/dist/types/message.d.ts

@@ -0,0 +1,3 @@
+export declare type Message = {
+    message?: string;
+};

package/dist/types/metadata.d.ts

@@ -0,0 +1,8 @@
+export declare type Metadata = {
+    request_id: string;
+    transaction_key: string;
+    sha256: string;
+    created: string;
+    duration: number;
+    channels: number;
+};

package/dist/types/prerecordedTranscriptionOptions.d.ts

@@ -0,0 +1,139 @@
+import { Models } from "../enums";
+/**
+ * Options for transcription
+ */
+export declare type PrerecordedTranscriptionOptions = {
+    /**
+     * AI model used to process submitted audio.
+     * @default general
+     * @remarks Possible values are general, phonecall, meeting or a custom string
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/model
+     */
+    model?: Models | string;
+    /**
+     * Version of the model to use.
+     * @default latest
+     * @remarks latest OR <version_id>
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/version
+     */
+    version?: string;
+    /**
+     * Tier of the model to use.
+     * @default base
+     * @remarks Possible values are base or enhanced
+     * @see https://developers.deepgram.com/documentation/features/tier/
+     */
+    tier?: string;
+    /**
+     * Terms or phrases to search for in the submitted audio and replace
+     * @remarks Can send multiple instances in query string replace=this:that&replace=thisalso:thatalso. Replacing a term or phrase with nothing will remove the term or phrase from the audio transcript.
+     * @see https://developers.deepgram.com/documentation/features/replace/
+     */
+    replace?: string;
+    /**
+     * BCP-47 language tag that hints at the primary spoken language.
+     * @default en-US
+     * @remarks Possible values are en-GB, en-IN, en-NZ, en-US, es, fr, ko, pt,
+     * pt-BR, ru, tr or null
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/language
+     */
+    language?: string;
+    /**
+     * Indicates whether to add punctuation and capitalization to the transcript.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/punctuate
+     */
+    punctuate?: boolean;
+    /**
+     * Indicates whether to remove profanity from the transcript.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/profanity_filter
+     */
+    profanity_filter?: boolean;
+    /**
+     * Indicates whether to redact sensitive information, replacing redacted content with asterisks (*).
+     * @remarks Options include:
+     *  `pci`: Redacts sensitive credit card information, including credit card number, expiration date, and CVV
+     *  `numbers` (or `true)`: Aggressively redacts strings of numerals
+     *  `ssn` (*beta*): Redacts social security numbers
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/redact
+     */
+    redact?: Array<string>;
+    /**
+     * Indicates whether to recognize speaker changes. When set to true, each word
+     * in the transcript will be assigned a speaker number starting at 0.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/diarize
+     */
+    diarize?: boolean;
+    /**
+     * Indicates whether to transcribe each audio channel independently. When set
+     * to true, you will receive one transcript for each channel, which means you
+     * can apply a different model to each channel using the model parameter (e.g.,
+     * set model to general:phonecall, which applies the general model to channel
+     * 0 and the phonecall model to channel 1).
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/multichannel
+     */
+    multichannel?: boolean;
+    /**
+     * Maximum number of transcript alternatives to return. Just like a human listener,
+     * Deepgram can provide multiple possible interpretations of what it hears.
+     * @default 1
+     */
+    alternatives?: number;
+    /**
+     * Indicates whether to convert numbers from written format (e.g., one) to
+     * numerical format (e.g., 1). Deepgram can format numbers up to 999,999.
+     * @remarks Converted numbers do not include punctuation. For example,
+     * 999,999 would be transcribed as 999999.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/numerals
+     */
+    numerals?: boolean;
+    /**
+     * Terms or phrases to search for in the submitted audio. Deepgram searches
+     * for acoustic patterns in audio rather than text patterns in transcripts
+     * because we have noticed that acoustic pattern matching is more performant.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/search
+     */
+    search?: Array<string>;
+    /**
+     * Callback URL to provide if you would like your submitted audio to be
+     * processed asynchronously. When passed, Deepgram will immediately respond
+     * with a request_id. When it has finished analyzing the audio, it will send
+     * a POST request to the provided URL with an appropriate HTTP status code.
+     * @remarks You may embed basic authentication credentials in the callback URL.
+     * Only ports 80, 443, 8080, and 8443 can be used for callbacks.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/callback
+     */
+    callback?: string;
+    /**
+     * Keywords to which the model should pay particular attention to boosting
+     * or suppressing to help it understand context. Just like a human listener,
+     * Deepgram can better understand mumbled, distorted, or otherwise
+     * hard-to-decipher speech when it knows the context of the conversation.
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/keywords
+     */
+    keywords?: Array<string>;
+    /**
+     * Indicates whether Deepgram will segment speech into meaningful semantic
+     * units, which allows the model to interact more naturally and effectively
+     * with speakers' spontaneous speech patterns. For example, when humans
+     * speak to each other conversationally, they often pause mid-sentence to
+     * reformulate their thoughts, or stop and restart a badly-worded sentence.
+     * When utterances is set to true, these utterances are identified and
+     * returned in the transcript results.
+     *
+     * By default, when utterances is enabled, it starts a new utterance after
+     * 0.8 s of silence. You can customize the length of time used to determine
+     * where to split utterances by submitting the utt_split parameter.
+     * @remarks **BETA FEATURE**
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/utterances
+     */
+    utterances?: boolean;
+    /**
+     * Length of time in seconds of silence between words that Deepgram will
+     * use when determining where to split utterances. Used when utterances
+     * is enabled.
+     * @default 0.8 seconds
+     * @remarks **BETA FEATURE**
+     * @see https://developers.deepgram.com/api-reference/speech-recognition-api#operation/transcribeAudio/properties/utt_split
+     */
+    utt_split?: number;
+};

package/dist/types/prerecordedTranscriptionResponse.d.ts

@@ -0,0 +1,25 @@
+import { Metadata } from "./metadata";
+import { Channel } from "./channel";
+import { Utterance } from "./utterance";
+export declare class PrerecordedTranscriptionResponse {
+    request_id?: string;
+    metadata?: Metadata;
+    results?: {
+        channels: Array<Channel>;
+        utterances?: Array<Utterance>;
+    };
+    /**
+     * Converts the transcription to the WebVTT format
+     * @remarks In order to translate the transcription to WebVTT, the utterances
+     * feature must be used.
+     * @returns A string with the transcription in the WebVTT format
+     */
+    toWebVTT(): string;
+    /**
+     * Converts the transcription to the SRT format
+     * @remarks In order to translate the transcription to SRT, the utterances
+     * feature must be used.
+     * @returns A string with the transcription in the SRT format
+     */
+    toSRT(): string;
+}

package/dist/types/project.d.ts

@@ -0,0 +1,17 @@
+/**
+ * Deepgram project
+ */
+export declare type Project = {
+    /**
+     * Unique identifier of the project
+     */
+    project_id: string;
+    /**
+     * User provided name of the project
+     */
+    name?: string;
+    /**
+     * Name of the company associated with the project. Optional.
+     */
+    company?: string;
+};

package/dist/types/projectPatchRequest.d.ts

@@ -0,0 +1,4 @@
+export declare type ProjectPatchRequest = {
+    name?: string;
+    company?: string;
+};

package/dist/types/projectPatchResponse.d.ts

@@ -0,0 +1,6 @@
+export declare type ProjectPatchResponse = {
+    /**
+     * Success message.
+     */
+    message: string;
+};

package/dist/types/projectResponse.d.ts

@@ -0,0 +1,4 @@
+import { Project } from "./project";
+export declare type ProjectResponse = {
+    projects: Array<Project>;
+};

package/dist/types/requestFunction.d.ts

@@ -0,0 +1,5 @@
+/// <reference types="node" />
+import { ReadStream } from "fs";
+export declare type RequestFunction = NodeRequest | BrowserRequest;
+export declare type NodeRequest = (method: string, api_key: string, apiUrl: string, path: string, payload?: string | Buffer | ReadStream, options?: Object) => Promise<any>;
+export declare type BrowserRequest = (method: string, api_key: string, apiUrl: string, path: string, payload?: string) => Promise<any>;

package/dist/types/scopeList.d.ts

@@ -0,0 +1,3 @@
+export declare type ScopeList = {
+    scopes: Array<string>;
+};

package/dist/types/search.d.ts

@@ -0,0 +1,14 @@
+import { Hit } from "./hit";
+/**
+ * Search result for a transcription
+ */
+export declare type Search = {
+    /**
+     * Term for which Deepgram is searching.
+     */
+    query: string;
+    /**
+     * Instances of query found in transcript
+     */
+    hits: Array<Hit>;
+};

package/dist/types/transcriptionSource.d.ts

@@ -0,0 +1,14 @@
+/// <reference types="node" />
+import { Readable } from "stream";
+export declare type TranscriptionSource = UrlSource | BufferSource | ReadStreamSource;
+export declare type ReadStreamSource = {
+    stream: Readable;
+    mimetype: string;
+};
+export declare type UrlSource = {
+    url: string;
+};
+export declare type BufferSource = {
+    buffer: Buffer;
+    mimetype: string;
+};

package/dist/types/usageCallback.d.ts

@@ -0,0 +1,4 @@
+export declare type UsageCallback = {
+    code: number;
+    completed: string;
+};

package/dist/types/usageField.d.ts

@@ -0,0 +1,7 @@
+export declare type UsageField = {
+    tags: Array<string>;
+    models: Array<string>;
+    processing_methods: Array<string>;
+    languages: Array<string>;
+    features: Array<string>;
+};

package/dist/types/usageFieldOptions.d.ts

@@ -0,0 +1,4 @@
+export declare type UsageFieldOptions = {
+    start?: string;
+    end?: string;
+};

package/dist/types/usageOptions.d.ts

@@ -0,0 +1,23 @@
+export declare type UsageOptions = {
+    start?: string;
+    end?: string;
+    accessor?: string;
+    tag?: Array<string>;
+    method?: "sync" | "async" | "streaming";
+    model?: string;
+    multichannel?: boolean;
+    interim_results?: boolean;
+    punctuate?: boolean;
+    ner?: boolean;
+    utterances?: boolean;
+    replace?: boolean;
+    profanity_filter?: boolean;
+    keywords?: boolean;
+    sentiment?: boolean;
+    diarize?: boolean;
+    detect_language?: boolean;
+    search?: boolean;
+    redact?: boolean;
+    alternatives?: boolean;
+    numerals?: boolean;
+};

package/dist/types/usageRequest.d.ts

@@ -0,0 +1,11 @@
+import { UsageCallback } from "./usageCallback";
+import { UsageRequestDetail } from "./usageRequestDetail";
+import { UsageRequestMessage } from "./usageRequestMessage";
+export declare type UsageRequest = {
+    request_id: string;
+    created: string;
+    path: string;
+    accessor: string;
+    response?: UsageRequestDetail | UsageRequestMessage;
+    callback?: UsageCallback;
+};