ChatGPTでビデオ会議を強化：ライブAIアシスタントのご紹介

git clone https://github.com/hamzanasir/vonage-openai-demo

npm install

cp .envcopy .env

# enter your TokBox API key after the '=' sign below
TOKBOX_API_KEY=your_api_key

# enter your TokBox api secret after the '=' sign below
TOKBOX_SECRET=your_project_secret

# enter your OpenAI Secret after the '=' sign below
OPENAI_SECRET=your_openai_secret

npm start

const publisherOptions = {
  insertMode: 'append',
  width: '100%',
  height: '100%',
  publishCaptions: true,
};
publisher = OT.initPublisher('publisher', publisherOptions, (err) => {
        if (err) {
          handleError(err);
        } else {
          session.publish(publisher, () => {
            if (error) {
              console.error(error);
            } else {
              const captionOnlySub = session.subscribe(
                publisher.stream,
                document.createElement('div'),
                {
                  audioVolume: 0
                },
              );
              speakText(greetingMessage);
              captionOnlySub.on('captionReceived', async (event) => {
                if (event.isFinal) {
                  stopAiGenerator();
                  startAiGenerator(event.caption)
                }
              });
            }
          });
        }
      });

async function startAiGenerator(message) {
  let aiText = '';
  let utterableText = ''

  abortController = new AbortController();
  const userMessage = {
    'role': 'user',
    'content': message
  }

  const reqBody = {
    messages: [...messages, userMessage],
    temperature: 1,
    max_tokens: 256,
    top_p: 1,
    frequency_penalty: 0,
    presence_penalty: 0,
    model: 'gpt-3.5-turbo',
    stream: true
  };

  try {
    const response = await fetch('https://api.openai.com/v1/chat/completions', {
      headers: {
        'Authorization': `Bearer ${openAISecret}`,
        'Content-Type': 'application/json',
      },
      body: JSON.stringify(reqBody),
      method: 'POST',
      signal: abortController.signal
    });

function stopAiGenerator() {
  if (abortController) {
    abortController.abort();
    abortController = null;
  }
  window.speechSynthesis.cancel();
}

    const reader = response.body.getReader();
    const decoder = new TextDecoder('utf-8');

    while (true) {
      const chunk = await reader.read();
      const { done, value } = chunk;
      if (done) {
        break;
      }

      const decodedChunk = decoder.decode(value);
      const lines = decodedChunk.split('\n');
      const parsedLines = lines
        .map(l => l.replace(/^data: /, '').trim())
        .filter(l => l !== '' && l !== '[DONE]')
        .map(l => JSON.parse(l));
      for (const line of parsedLines) {
        const textChunk = line?.choices[0]?.delta?.content;
        if (textChunk) {
          utterableText += textChunk
          if (textChunk.match(/[.!?:,]$/)) {
            speakText(utterableText);
            utterableText = '';
          }
          aiText += textChunk;
        }
      }
    }

messages.push(userMessage);
  messages.push({
    content: aiText,
    role: 'assistant'
  })

const messages = [
  {
    'role': 'system',
    'content': "You are a participant called Sushi in a live call with someone. Speak concisely, as if you're having a one-on-one conversation with someone. " // Prompt engineering for AI assistant
  }
];

function speakText(text) {
  let captions = '';
  const utterThis = new SpeechSynthesisUtterance(text);

  utterThis.voice = voices.find((v) => v.name.includes('Samantha'));

  utterThis.onboundary = (event) => {
    captions += `${event.utterance.text.substring(event.charIndex, event.charIndex + event.charLength)} `;
    displayCaptions(captions, 'ai-assistant');
  };

  utterThis.onstart = () => {
    animateVoiceSynthesis();
  };

  utterThis.onend = function() {
    stopAnimateVoiceSynthesis();
  };

  window.speechSynthesis.speak(utterThis);
}

let voices = window.speechSynthesis.getVoices();

if (speechSynthesis.onvoiceschanged !== undefined)
  speechSynthesis.onvoiceschanged = updateVoices;

function updateVoices() {
  voices = window.speechSynthesis.getVoices();
}