Function for extracting text from speech. It sends a request to the Speech Extraction AI Model and returns the extracted text. Read more about the Models and their use cases at: https://docs.worqhat.com/ai-models/speech-extraction

​
Parameters

ParameterTypeDescriptionDefault
audiofileAudio file to extract text from.-

The audio file should be in one of the following formats: wav, mp3, m4a, flac, ogg, opus, amr, webm.

​
Initialize AI Modules

const worqhat = require('worqhat');

var config = new worqhat.Configuration({
    apiKey: "your-api-key",
    debug: true,
    max_retries: 3,
});


worqhat.initializeApp(config);

let ai = worqhat.ai();

​
Implementation

ai.textExtraction.speech({
    audio: "bark.wav"
}).then(function(response) {
    console.log(response);
}).catch(function(error) {
    console.log(error);
});

Was this page helpful?

Image Extraction AIText and Content Moderation AI