@kkaczynski/use-whisper v0.1.4

useWhisper

React Hook for OpenAI Whisper API with speech recorder and real-time transcription.

• Demo

• Real-Time transcription demo

https://user-images.githubusercontent.com/2707253/224465747-0b1ee159-21dd-4cd0-af9d-6fc9b882d716.mp4

• Install

npm i @kkaczynski/use-whisper

yarn add @kkaczynski/use-whisper

• Usage

import { useWhisper } from '@kkaczynski/use-whisper'

const App = () => {
  const {
    recording,
    speaking,
    transcribing,
    transcript,
    pauseRecording,
    startRecording,
    stopRecording,
  } = useWhisper({
    apiKey: process.env.OPENAI_API_TOKEN, // YOUR_OPEN_AI_TOKEN
  })

  return (
    <div>
      <p>Recording: {recording}</p>
      <p>Speaking: {speaking}</p>
      <p>Transcribing: {transcribing}</p>
      <p>Transcribed Text: {transcript.text}</p>
      <button onClick={() => startRecording()}>Start</button>
      <button onClick={() => pauseRecording()}>Pause</button>
      <button onClick={() => stopRecording()}>Stop</button>
    </div>
  )
}

• Custom Server (keep OpenAI API token secure)

import { useWhisper } from '@kkaczynski/use-whisper'

const App = () => {
  /**
   * you have more control like this
   * do whatever you want with the recorded speech
   * send it to your own custom server
   * and return the response back to useWhisper
   */
  const onTranscribe = (blob: Blob) => {
    const base64 = await new Promise<string | ArrayBuffer | null>(
      (resolve) => {
        const reader = new FileReader()
        reader.onloadend = () => resolve(reader.result)
        reader.readAsDataURL(blob)
      }
    )
    const body = JSON.stringify({ file: base64, model: 'whisper-1' })
    const headers = { 'Content-Type': 'application/json' }
    const { default: axios } = await import('axios')
    const response = await axios.post('/api/whisper', body, {
      headers,
    })
    const { text } = await response.data
    // you must return result from your server in Transcript format
    return {
      blob,
      text,
    }
  }

  const { transcript } = useWhisper({
    // callback to handle transcription with custom server
    onTranscribe,
  })

  return (
    <div>
      <p>{transcript.text}</p>
    </div>
  )
}

• Examples

• Real-time streaming trascription

import { useWhisper } from '@kkaczynski/use-whisper'

const App = () => {
  const { transcript } = useWhisper({
    apiKey: process.env.OPENAI_API_TOKEN, // YOUR_OPEN_AI_TOKEN
    streaming: true,
    timeSlice: 1_000, // 1 second
    whisperConfig: {
      language: 'en',
    },
  })

  return (
    <div>
      <p>{transcript.text}</p>
    </div>
  )
}

• Remove silence before sending to Whisper to save cost

import { useWhisper } from '@kkaczynski/use-whisper'

const App = () => {
  const { transcript } = useWhisper({
    apiKey: process.env.OPENAI_API_TOKEN, // YOUR_OPEN_AI_TOKEN
    // use ffmpeg-wasp to remove silence from recorded speech
    removeSilence: true,
  })

  return (
    <div>
      <p>{transcript.text}</p>
    </div>
  )
}

• Auto start recording on component mounted

import { useWhisper } from '@kkaczynski/use-whisper'

const App = () => {
  const { transcript } = useWhisper({
    apiKey: process.env.OPENAI_API_TOKEN, // YOUR_OPEN_AI_TOKEN
    // will auto start recording speech upon component mounted
    autoStart: true,
  })

  return (
    <div>
      <p>{transcript.text}</p>
    </div>
  )
}

• Keep recording as long as the user is speaking

import { useWhisper } from '@kkaczynski/use-whisper'

const App = () => {
  const { transcript } = useWhisper({
    apiKey: process.env.OPENAI_API_TOKEN, // YOUR_OPEN_AI_TOKEN
    nonStop: true, // keep recording as long as the user is speaking
    stopTimeout: 5000, // auto stop after 5 seconds
  })

  return (
    <div>
      <p>{transcript.text}</p>
    </div>
  )
}

• Customize Whisper API config when autoTranscribe is true

import { useWhisper } from '@kkaczynski/use-whisper'

const App = () => {
  const { transcript } = useWhisper({
    apiKey: process.env.OPENAI_API_TOKEN, // YOUR_OPEN_AI_TOKEN
    autoTranscribe: true,
    whisperConfig: {
      prompt: 'previous conversation', // you can pass previous conversation for context
      response_format: 'text', // output text instead of json
      temperature: 0.8, // random output
      language: 'es', // Spanish
    },
  })

  return (
    <div>
      <p>{transcript.text}</p>
    </div>
  )
}

• Dependencies

  • @chengsokdara/react-hooks-async asynchronous react hooks
  • recordrtc: cross-browser audio recorder
  • hark: for speaking detection
  • axios: since fetch does not work with Whisper endpoint

most of these dependecies are lazy loaded, so it is only imported when it is needed

• API

• Config Object

• WhisperApiConfig

• Return Object

• Transcript

• Roadmap

  • react-native support, will be export as use-whisper/native