jaemil Posts - Answer Overflow

jaemil

Explore posts from servers

DIAdiscord.js - Imagine an app RRailway TTCTheo's Typesafe Cult

•Created by jaemil on 3/22/2024 in #djs-voice

Problem saving audioBuffer to file - whisper api

Hi, how can i convert the audioBuffer into a e.g. wav file? I want to use whisper for spech regognition. this is my code:

const tmpFile = await new Promise((resolve, reject) => {
    tmp.file({ postfix: ".ogg" }, (err, path, fd, cleanup) => {
      if (err) {
        reject(err);
        return;
      }

      fs.writeFile(path, msg.audioBuffer, (err) => {
        if (err) {
          reject(err);
          return;
        }

        resolve({ path, cleanup });
      });
    });
  });

const tmpFile = await new Promise((resolve, reject) => {
    tmp.file({ postfix: ".ogg" }, (err, path, fd, cleanup) => {
      if (err) {
        reject(err);
        return;
      }

      fs.writeFile(path, msg.audioBuffer, (err) => {
        if (err) {
          reject(err);
          return;
        }

        resolve({ path, cleanup });
      });
    });
  });

The file is written successfully, but I can't play it (unrecognized file format) I also tried to post audioBuffer directly, but that doesn't work either.

async function resolveSpeechWithWhisper(audioBuffer) {
  const transcription = await openai.audio.transcriptions.create({
    file: audioBuffer,
    model: "whisper-1",
    response_format: "verbose_json",
    timestamp_granularities: ["word"],
  });
}

async function resolveSpeechWithWhisper(audioBuffer) {
  const transcription = await openai.audio.transcriptions.create({
    file: audioBuffer,
    model: "whisper-1",
    response_format: "verbose_json",
    timestamp_granularities: ["word"],
  });
}

error: BadRequestError: 400 Could not parse multipart form at APIError.generate (/home/git/discord-speech-recognition/examples/simpleBot/node_modules/openai/error.js:44:20) at OpenAI.makeStatusError (/home/git/discord-speech-recognition/examples/simpleBot/node_modules/openai/core.js:263:33) at OpenAI.makeRequest (/home/git/discord-speech-recognition/examples/simpleBot/node_modules/openai/core.js:306:30) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async Object.resolveSpeechWithWhisper [as speechRecognition] (/home/git/discord-speech-recognition/examples/simpleBot/index.js:20:25) {

"@discordjs/opus": "^0.8.0",
    "@discordjs/voice": "^0.11.0",
    "discord-speech-recognition": "^3.4.1",
    "discord.js": "^14.3.0",
    "dotenv": "^16.4.5",
    "openai": "^4.29.2",
    "tmp": "^0.2.3",
    "tweetnacl": "^1.0.3"

"@discordjs/opus": "^0.8.0",
    "@discordjs/voice": "^0.11.0",
    "discord-speech-recognition": "^3.4.1",
    "discord.js": "^14.3.0",
    "dotenv": "^16.4.5",
    "openai": "^4.29.2",
    "tmp": "^0.2.3",
    "tweetnacl": "^1.0.3"

Can anyone help me with this? Thanks

8 replies

Gaming

Programming