Telegram-bot för transkribering

CREATE TABLE IF NOT EXISTS transcription_logs (
  id BIGSERIAL PRIMARY KEY,
  file_type VARCHAR NOT NULL,
  duration INTEGER NOT NULL,
  chat_id BIGINT NOT NULL,
  message_id BIGINT NOT NULL,
  username VARCHAR,
  transcript TEXT,
  language_code VARCHAR,
  created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP,
  error TEXT
);
ALTER TABLE transcription_logs ENABLE ROW LEVEL SECURITY;

# Find / create an API key at https://elevenlabs.io/app/settings/api-keys
ELEVENLABS_API_KEY=your_api_key
# The bot token you received from the BotFather.
TELEGRAM_BOT_TOKEN=your_bot_token
# A random secret chosen by you to secure the function.
FUNCTION_SECRET=random_secret

import { Bot, webhookCallback } from "https://deno.land/x/grammy@v1.34.0/mod.ts";
import "jsr:@supabase/functions-js/edge-runtime.d.ts";
import { createClient } from "jsr:@supabase/supabase-js@2";
import { ElevenLabsClient } from "npm:elevenlabs@1.50.5";
console.log(`Function "elevenlabs-scribe-bot" up and running!`);
const elevenlabs = new ElevenLabsClient({
  apiKey: Deno.env.get("ELEVENLABS_API_KEY") || "",
});
const supabase = createClient(
  Deno.env.get("SUPABASE_URL") || "",
  Deno.env.get("SUPABASE_SERVICE_ROLE_KEY") || ""
);
async function scribe({
  fileURL,
  fileType,
  duration,
  chatId,
  messageId,
  username,
}: {
  fileURL: string;
  fileType: string;
  duration: number;
  chatId: number;
  messageId: number;
  username: string;
}) {
  let transcript: string | null = null;
  let languageCode: string | null = null;
  let errorMsg: string | null = null;
  try {
    const sourceFileArrayBuffer = await fetch(fileURL).then((res) => res.arrayBuffer());
    const sourceBlob = new Blob([sourceFileArrayBuffer], {
      type: fileType,
    });
    const scribeResult = await elevenlabs.speechToText.convert({
      file: sourceBlob,
      model_id: "scribe_v2",
      tag_audio_events: false,
    });
    transcript = scribeResult.text;
    languageCode = scribeResult.language_code;
    // Reply to the user with the transcript
    await bot.api.sendMessage(chatId, transcript, {
      reply_parameters: { message_id: messageId },
    });
  } catch (error) {
    errorMsg = error.message;
    console.log(errorMsg);
    await bot.api.sendMessage(chatId, "Sorry, there was an error. Please try again.", {
      reply_parameters: { message_id: messageId },
    });
  }
  // Write log to Supabase.
  const logLine = {
    file_type: fileType,
    duration,
    chat_id: chatId,
    message_id: messageId,
    username,
    language_code: languageCode,
    error: errorMsg,
  };
  console.log({ logLine });
  await supabase.from("transcription_logs").insert({ ...logLine, transcript });
}
const telegramBotToken = Deno.env.get("TELEGRAM_BOT_TOKEN");
const bot = new Bot(telegramBotToken || "");
const startMessage = `Welcome to the ElevenLabs Scribe Bot\\! I can transcribe speech in 90\\+ languages with super high accuracy\\!
    \nTry it out by sending or forwarding me a voice message, video, or audio file\\!
    \n[Learn more about Scribe](https://elevenlabs.io/speech-to-text) or [build your own bot](https://elevenlabs.io/developers/guides/cookbooks/speech-to-text/telegram-bot)\\!
  `;
bot.command("start", (ctx) => ctx.reply(startMessage.trim(), { parse_mode: "MarkdownV2" }));
bot.on([":voice", ":audio", ":video"], async (ctx) => {
  try {
    const file = await ctx.getFile();
    const fileURL = `https://api.telegram.org/file/bot${telegramBotToken}/${file.file_path}`;
    const fileMeta = ctx.message?.video ?? ctx.message?.voice ?? ctx.message?.audio;
    if (!fileMeta) {
      return ctx.reply("No video|audio|voice metadata found. Please try again.");
    }
    // Run the transcription in the background.
    EdgeRuntime.waitUntil(
      scribe({
        fileURL,
        fileType: fileMeta.mime_type!,
        duration: fileMeta.duration,
        chatId: ctx.chat.id,
        messageId: ctx.message?.message_id!,
        username: ctx.from?.username || "",
      })
    );
    // Reply to the user immediately to let them know we received their file.
    return ctx.reply("Received. Scribing...");
  } catch (error) {
    console.error(error);
    return ctx.reply(
      "Sorry, there was an error getting the file. Please try again with a smaller file!"
    );
  }
});
const handleUpdate = webhookCallback(bot, "std/http");
Deno.serve(async (req) => {
  try {
    const url = new URL(req.url);
    if (url.searchParams.get("secret") !== Deno.env.get("FUNCTION_SECRET")) {
      return new Response("not allowed", { status: 405 });
    }
    return await handleUpdate(req);
  } catch (err) {
    console.error(err);
  }
});