// Official Discord BOT voice joiner (replaces the selfbot join.mjs). // // Why this exists: the project migrated off the user-token selfbot path onto an // official bot application. For the voice loop (STT input) this is the fully // supported, ToS-safe path — @discordjs/voice lets a bot JOIN a voice channel, // pass the DAVE/MLS E2EE handshake (via @snazzah/davey, handled internally), and // RECEIVE per-user Opus audio. Only screenshare VIDEO receive still requires a // selfbot, and video ("눈") is deferred, so nothing here needs a user token. // // This replicates M1 (join target channel, stay, detect speakers) and, for free, // gives partial M2: it decodes each speaker's Opus to PCM and counts frames — the // exact stream the STT stage will consume. // // Usage: // node bot.mjs # join and stay until killed // RUN_MS=15000 node bot.mjs # join, hold 15s, then leave (for verification) // // Requires: the bot must be INVITED to the target guild with the "Connect" and // "Speak" voice permissions. See dave/README or run `node bot.mjs --invite`. import fs from 'node:fs'; import { Client, GatewayIntentBits, } from 'discord.js'; import { joinVoiceChannel, getVoiceConnection, entersState, VoiceConnectionStatus, EndBehaviorType, } from '@discordjs/voice'; import prism from 'prism-media'; // ---------- config ---------- function loadEnvFile() { try { return Object.fromEntries( fs.readFileSync(new URL('../.env', import.meta.url), 'utf8') .split('\n').filter(l => l && !l.startsWith('#') && l.includes('=')) .map(l => { const i = l.indexOf('='); return [l.slice(0, i).trim(), l.slice(i + 1).trim()]; }) ); } catch { return {}; } } const env = loadEnvFile(); const TOKEN = process.env.DISCORD_BOT_TOKEN || env.DISCORD_BOT_TOKEN; const GUILD_ID = process.env.GUILD_ID || env.GUILD_ID || '1352269198297923648'; const CHANNEL_ID = process.env.CHANNEL_ID || env.CHANNEL_ID || '1352269198914621465'; const RUN_MS = process.env.RUN_MS != null ? Number(process.env.RUN_MS) : 0; // 0 = stay forever const t0 = Date.now(); const log = (...a) => console.log(`[+${String(Date.now() - t0).padStart(6)}ms]`, ...a); // ---------- invite URL helper ---------- // A bot cannot add itself to a server; a server admin must click an OAuth2 invite // URL once. Print it so the user can authorise the bot with voice permissions. if (process.argv.includes('--invite')) { const APP_ID = process.env.DISCORD_APP_ID || env.DISCORD_APP_ID || ''; // permissions: Connect(1<<20) | Speak(1<<21) | UseVAD(1<<25) | ViewChannel(1<<10) const perms = (1n << 20n) | (1n << 21n) | (1n << 25n) | (1n << 10n); if (!APP_ID) { console.error('set DISCORD_APP_ID (application/client id) in .env to build the invite URL'); process.exit(2); } console.log(`https://discord.com/oauth2/authorize?client_id=${APP_ID}&scope=bot&permissions=${perms}`); process.exit(0); } if (!TOKEN) { console.error('no DISCORD_BOT_TOKEN in env or ../.env'); process.exit(2); } // ---------- client ---------- const client = new Client({ intents: [GatewayIntentBits.Guilds, GatewayIntentBits.GuildVoiceStates], }); const perUser = new Map(); // userId -> { opusPackets, pcmFrames } let leaving = false; function leaveAndExit(code = 0) { if (leaving) return; leaving = true; try { getVoiceConnection(GUILD_ID)?.destroy(); } catch {} const summary = [...perUser.entries()].map(([u, s]) => `${u}:opus=${s.opusPackets},pcm=${s.pcmFrames}`); log(`leaving. speakers heard: ${summary.length ? summary.join(' ') : '(none)'}`); try { client.destroy(); } catch {} setTimeout(() => process.exit(code), 300); } process.on('SIGINT', () => { log('SIGINT'); leaveAndExit(0); }); process.on('SIGTERM', () => { log('SIGTERM'); leaveAndExit(0); }); // Hard time-box ceiling, armed at startup regardless of handshake state. if (RUN_MS > 0) setTimeout(() => { log(`RUN_MS=${RUN_MS} hard ceiling elapsed — leaving`); leaveAndExit(0); }, RUN_MS); client.once('clientReady', async () => { log(`logged in as ${client.user.tag} (${client.user.id})`); let guild, channel; try { guild = await client.guilds.fetch(GUILD_ID); channel = await guild.channels.fetch(CHANNEL_ID); } catch (e) { log(`FATAL: cannot access guild/channel — is the bot invited to guild ${GUILD_ID}? (${e.message})`); log('run `node bot.mjs --invite` and have a server admin authorise the bot, then retry.'); return leaveAndExit(1); } if (!channel || !channel.isVoiceBased()) { log(`FATAL: channel ${CHANNEL_ID} is not a voice channel`); return leaveAndExit(1); } log(`joining voice: guild="${guild.name}" channel="${channel.name}"`); const connection = joinVoiceChannel({ channelId: CHANNEL_ID, guildId: GUILD_ID, adapterCreator: guild.voiceAdapterCreator, selfDeaf: false, // MUST be false to receive audio (the STT input path) selfMute: false, // false so we can also speak later (M5 TTS) }); try { await entersState(connection, VoiceConnectionStatus.Ready, 20_000); } catch (e) { log(`FATAL: voice connection did not become Ready in 20s (${e.message})`); return leaveAndExit(1); } log(`✅ JOINED & READY. channel=${CHANNEL_ID} — staying connected, listening for speakers…`); // ---------- receive path (partial M2) ---------- const receiver = connection.receiver; receiver.speaking.on('start', (userId) => { if (!perUser.has(userId)) perUser.set(userId, { opusPackets: 0, pcmFrames: 0 }); log(`SPEAKING start user=${userId}`); const opusStream = receiver.subscribe(userId, { end: { behavior: EndBehaviorType.AfterSilence, duration: 500 }, }); // Decode Opus -> 48kHz stereo s16le PCM (what faster-whisper will consume, downsampled to 16k in M3). const decoder = new prism.opus.Decoder({ rate: 48000, channels: 2, frameSize: 960 }); opusStream.on('data', () => { perUser.get(userId).opusPackets++; }); opusStream.pipe(decoder); decoder.on('data', () => { const s = perUser.get(userId); s.pcmFrames++; if (s.pcmFrames === 1 || s.pcmFrames % 200 === 0) log(`rtp: user=${userId} opus=${s.opusPackets} pcm=${s.pcmFrames}`); }); decoder.on('error', (e) => log(`decode error user=${userId}: ${e.message}`)); }); connection.on(VoiceConnectionStatus.Disconnected, () => { log('voice: disconnected — attempting to resume…'); Promise.race([ entersState(connection, VoiceConnectionStatus.Signalling, 5_000), entersState(connection, VoiceConnectionStatus.Connecting, 5_000), ]).catch(() => { log('voice: could not resume, leaving'); leaveAndExit(0); }); }); }); client.on('error', (e) => log('client error', e.message)); client.login(TOKEN).catch((e) => { log(`FATAL: login failed — ${e.message}`); process.exit(1); });