Sofya Transcription

Sofya Transcription is a JavaScript library that provides a robust and flexible solution for real-time audio transcription. It is designed to transcribe audio streams and can be easily integrated into web applications. The library also includes a functionality for capturing audio from media elements.

Features

• Real-Time Transcription: Transcribe audio streams in real time with high accuracy.
• Flexible Integration: Seamlessly integrates with your web applications.
• Media Element Audio Capture: Feature to capture audio from media elements like <video> and <audio>.

Installation

To install Sofya Transcription, you can use npm:

npm install sofya.transcription

Usage

Here's a basic example of how to use Sofya Transcription in your project:

1. Import the Library:

   import { MediaElementAudioCapture, TranscriptionService } from 'sofya.transcription';

2. Create a Transcription Service Instance: const transcriptionConfig = {language: 'pt-BR', model: 'YOUR_MODEL_ID', region: 'YOUR_REGION'} const transcriber = new TranscriptionService('YOUR_API_KEY', transcriptionConfig);

3. Initialize and Start Transcription:

   const mediaStream = await navigator.mediaDevices.getUserMedia(); transcriber.startTranscription(mediaStream);

4. Handle Transcription Events:

   transcriber.on('recognizing', (text) => { console.log('Recognizing: ' + text); });

   transcriber.on('recognized', (text) => { console.log('Recognized: ' + text); });

   transcriber.on('nomatch', () => { console.log('No match found.'); });

5. Stop Transcription:

   transcriber.stopTranscription();

API

TranscriptionService

• constructor('YOUR_API_KEY', config): Creates a new instance of the transcription service with a given API KEY and an config object.

• startTranscription(): void: Starts the transcription process with a given MediaStream.

• stopTranscription(): void: Stops the transcription process.

• on(event: string, callback: Function): void: Registers an event handler for transcription events. Possible events include:

  • recognizing: Fired when transcription is in progress.
  • recognized: Fired when transcription is complete.
  • nomatch: Fired when no speech is recognized.

• React Example

import React from 'react'
import { SofyaTranscriber } from 'sofya.transcription'
export const App = () => {
  const transcriber = React.useRef(null)
  const [transcription, setTranscription] = React.useState('')
  const transcriptionRef = React.useRef('')

  const getMediaStream = async () => {
    const stream = await navigator.mediaDevices.getUserMedia({ audio: true })
    return stream
  }

  const startTranscription = async () => {
    try {
      const stream = await getMediaStream()
      const transcriber = new SofyaTranscriber(
        'your_key',
        {
          language: 'pt-BR',
          model: 'your_model',
          region: 'your_region',
        }
      )

      transcriber.startTranscription(stream)
      transcriber.on('recognizing', (result: string) => {
        console.log({ recognizing: result })
        setTranscription(transcriptionRef.current + result)
      })

      transcriber.on('recognized', (result: string) => {
        console.log({ recognized: result })
        setTranscription(transcriptionRef.current + result)
        transcriptionRef.current = transcriptionRef.current + result
      })
      transcriber.current = transcriber
    } catch (error) {
      console.log({ error })
    }
  }

  const stopTranscription = () => {
    if (transcriber.current) {
      transcriber.current.stopTranscription()
      transcriber.current = null
    }
  }

  return (
    <div>
      <button onClick={startTranscription}>Start Transcription</button>
      <button onClick={stopTranscription}>Stop Transcription</button>
      <hr />
      <p>{transcription}</p>
    </div>
  )
}

MediaElementAudioCapture

• constructor(): Creates a new instance of the media element audio capture.

• captureAudio(mediaElement: HTMLMediaElement): MediaStream: Captures the audio stream from a given media element and returns a MediaStream.