Simplified version of EzBot

index.js

require('dotenv').config()
const Discord = require('discord.js')
const config = require('./config')
const { Transform } = require('stream')
const googleSpeech = require('@google-cloud/speech')

async function playFile(connection, filePath) {
  return new Promise((resolve, reject) => {
    const dispatcher = connection.play(filePath)
    dispatcher.setVolume(1)
    dispatcher.on('start', () => {
      console.log('Playing')
    })
    dispatcher.on('end', () => {
      resolve()
    })
    dispatcher.on('error', (error) => {
      console.error(error)
      reject(error)
    })
  })
}

function convertBufferTo1Channel(buffer) {
  const convertedBuffer = Buffer.alloc(buffer.length / 2)

  for (let i = 0; i < convertedBuffer.length / 2; i++) {
    const uint16 = buffer.readUInt16LE(i * 4)
    convertedBuffer.writeUInt16LE(uint16, i * 2)
  }

  return convertedBuffer
}

class ConvertTo1ChannelStream extends Transform {
  constructor(source, options) {
    super(options)
  }

  _transform(data, encoding, next) {
    next(null, convertBufferTo1Channel(data))
  }
}

const discordClient = new Discord.Client()
const googleSpeechClient = new googleSpeech.SpeechClient()
const GamesAndChannels = {
  Mines: '[Voice Channel ID]'
}

discordClient.on('ready', () => {
  console.log(`Logged in as ${discordClient.user.tag}!`)
})

discordClient.on('presenceUpdate', async (oldPresence, newPresence) => {
  const member = newPresence.member
  const presence = newPresence
  const memberVoiceChannel = member.voice.channel

  if (!presence || !presence.activity || !presence.activity.name || !memberVoiceChannel) {
    return
  }

  const activityName = presence.activity.name
  const channelId = GamesAndChannels[activityName]

  if (!channelId) {
    return
  }

  const connection = await memberVoiceChannel.join()
  const receiver = connection.receiver

  await playFile(connection, 'audio/wrongChannelEn.mp3')

  setTimeout(() => {
    memberVoiceChannel.leave()
  }, 30000)

  console.log('I am ready to listen...')

  connection.on('speaking', (user, speaking) => {
    if (!speaking) {
      return
    }

    console.log(`I'm listening to ${user.username}`)

    // this creates a 16-bit signed PCM, stereo 48KHz stream
    const audioStream = receiver.createStream(user, { mode: 'pcm' })
    const requestConfig = {
      encoding: 'LINEAR16',
      sampleRateHertz: 48000,
      languageCode: 'en-US'
    }
    const request = {
      config: requestConfig,
      interimResults: true
    }
    const recognizeStream = googleSpeechClient
      .streamingRecognize(request)
      .on('error', console.error)
      .on('data', response => {
        const transcription = response.results
          .map(result => result.alternatives[0].transcript)
          .join('\n')
          .toLowerCase()
        console.log(`Transcription: ${transcription}`)

        if (transcription.indexOf('yes') > -1) {
          connection.channel.members.array().forEach(member => {
            if (member.user.id !== discordClient.user.id) {
              console.log(`Moving member ${member.displayName} to channel ${channelId}`)
              member.edit({ channel: channelId }).catch(console.error)
              memberVoiceChannel.leave()
              recognizeStream.destroy()
            }
          })
        } else if (transcription.indexOf('no') > -1) {
          memberVoiceChannel.leave()
          recognizeStream.destroy()
        }
      })

    const convertTo1ChannelStream = new ConvertTo1ChannelStream()

    audioStream.pipe(convertTo1ChannelStream).pipe(recognizeStream)

    audioStream.on('end', async () => {
      console.log('audioStream end')
    })
  })
})

discordClient.login(config.discordApiToken)