const { Deepgram } = require("@deepgram/sdk");

const deepgram = new Deepgram({
  apiKey: DEEPGRAM_API_KEY,
  apiUrl: CUSTOM_API_URL, // Optionally used for on-premises customers
});

// Sending a file
const fileSource = { url: URL_OF_FILE };

// Sending a buffer
const bufferSource = { buffer: BUFFER_OF_FILE, mimetype: MIMETYPE_OF_FILE };

// Both fileSource or bufferSource could be provided as the source parameter
const response = await deepgram.transcription.preRecorded(
  fileSource | bufferSource,
  {
    punctuate: true,
    // other options are available
  }
);

{
  /**
   * 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;
  /**
   * 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;
}

const deepgramLive = deepgram.transcription.live({ punctuate: true });

socket.on("microphone-stream", (stream) => {
  deepgramSocket.send(stream);
});

/**
 * Receive transcriptions based on sent streams
 */
deepgramLive.addListener("transcriptReceived", (transcription) => {
  console.log(transcription.data);
});

{
  /**
   * 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;
  /**
   * 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;
}

const projects = await deepgram.projects.list();

const project = await deepgram.projects.get(PROJECT_ID);

const updateResponse = await deepgram.projects.update(project);

const response = await deepgram.keys.list(PROJECT_ID);

const response = await deepgram.keys.create(PROJECT_ID, COMMENT_FOR_KEY);

await deepgram.keys.delete(PROJECT_ID, KEY_ID);

const response = await deepgram.usage.listRequests(PROJECT_ID, {
  limit: 10,
  // other options are available
});

{
  // The time to retrieve requests made since
  // Example: "2020-01-01T00:00:00+00:00"
  start?: string,
  // The time to retrieve requests made until
  // Example: "2021-01-01T00:00:00+00:00"
  end?: string,
  // Page of requests to return
  // Defaults to 0
  page?: number,
  // Number of requests to return per page
  // Defaults to 10. Maximum of 100
  limit?: number,
  // Filter by succeeded or failed requests
  // By default, all requests are returned
  status?: 'succeeded' | 'failed'
}

const response = await deepgram.usage.getRequest(PROJECT_ID, REQUEST_ID);

const response = await deepgram.usage.getUsage(PROJECT_ID, {
  start: "2020-01-01T00:00:00+00:00",
  // other options are available
});

{
  // The time to retrieve requests made since
  // Example: "2020-01-01T00:00:00+00:00"
  start?: string,
  // The time to retrieve requests made until
  // Example: "2021-01-01T00:00:00+00:00"
  end?: string,
  // Specific identifer for a request
  accessor?: string,
  // Array of tags used in requests
  tag?: Array<string>,
  // Filter requests by method
  method?: "sync" | "async" | "streaming",
  // Filter requests by model used
  model?: string,
  // Filter only requests using multichannel feature
  multichannel?: boolean,
  // Filter only requests using interim results feature
  interim_results?: boolean,
  // Filter only requests using the punctuation feature
  punctuate?: boolean,
  // Filter only requests using ner feature
  ner?: boolean,
  // Filter only requests using utterances feature
  utterances?: boolean,
  // Filter only requests using replace feature
  replace?: boolean,
  // Filter only requests using profanity_filter feature
  profanity_filter?: boolean,
  // Filter only requests using keywords feature
  keywords?: boolean,
  // Filter only requests using sentiment feature
  sentiment?: boolean,
  // Filter only requests using diarization feature
  diarize?: boolean,
  // Filter only requests using detect_language feature
  detect_language?: boolean,
  // Filter only requests using search feature
  search?: boolean,
  // Filter only requests using redact feature
  redact?: boolean,
  // Filter only requests using alternatives feature
  alternatives?: boolean,
  // Filter only requests using numerals feature
  numerals?: boolean
}

const response = await deepgram.usage.getUsage(PROJECT_ID, {
  start: "2020-01-01T00:00:00+00:00",
  // other options are available
});

{
  // The time to retrieve requests made since
  // Example: "2020-01-01T00:00:00+00:00"
  start?: string,
  // The time to retrieve requests made until
  // Example: "2021-01-01T00:00:00+00:00"
  end?: string
}

const config = {
  deepgramApiKey: "YOUR_DEEPGRAM_API_KEY",
  urlToFile:
    "https://static.deepgram.com/examples/Bueller-Life-moves-pretty-fast.wav",
};