Class: AudioConverterService

AudioConverterService()

Transcribes the given audio. It also detects the language, detects number of speakers, and diarizes. "file" or "url" is required, but not both should be provided.

Constructor

new AudioConverterService()

Source:

Methods

call(user, fileopt, urlopt, modelopt) → {Promise.<Object>}

Parameters:
Name Type Attributes Default Description
user string The ID of the user accessing the Soffos API. This string will be used for throttling and profanity tracking. Soffos assumes that the owner of the api is an application (app) and that app has users. Soffos API will accept any string."
file object <optional>
 null The audio file to be transcribed.
url string <optional>
 null The location of the audio file to be transcribed. Make sure it can be accessed publicly. If not, include the athentication strings of the url.
model string <optional>
 null The model to be used by the audio converter. Can be 'nova 2' or 'whisper'. Defaults to 'nova 2'.
Source:
Returns:
number_of_speakers - The number of speakers detected. transcripts - The transcription of the audio file or url. language - The detected language used by the speakers. error - * Description missing.
Type
Promise.<Object>
Example
Examples are available at "https://github.com/Soffos-Inc/soffosai-js/tree/master/samples"

setInputConfigs(name, fileopt, urlopt, modelopt)

Parameters:
Name Type Attributes Default Description
name string Reference name of this Service. It will be used by the Pipeline to reference this Service.
file object | InputConfig <optional>
 null The audio file to be transcribed.
url string | InputConfig <optional>
 null The location of the audio file to be transcribed. Make sure it can be accessed publicly. If not, include the athentication strings of the url.
model string | InputConfig <optional>
 null The model to be used by the audio converter. Can be 'nova 2' or 'whisper'. Defaults to 'nova 2'.
Source: