Transcriber

Motivation

TTS with VAD comes in handy in more than one project. Therefore, I want to wrap it into a re-usable package.

Usage

const {wait, proceed} = createWaitProceedSignal();

const transcriber = new Transcriber({
  transcriptionClient: new GoogleTranscriptionClient(),
  onMessage: async message => {
    console.log(message);
  },
  onError: async error => {
    console.error(error);
  }
});

console.log("Recording");
transcriber.start();

const handleExit = () => {
  transcriber.stop();
  process.off("SIGINT", handleExit);
  process.off("SIGTERM", handleExit);
  proceed();
};
process.on("SIGINT", handleExit);
process.on("SIGTERM", handleExit);

await wait;
console.log("Stopped");

If you don't want to pass the API key in the TranscriptionClient's constructor you can set the following environment variables:

• For Groq: GROQ_API_KEY
• For OpenAI: OPENAI_API_KEY
• For Google: GEMINI_API_KEY

License

This project is licensed under the MIT License. See the LICENSE file for details.