feat(selfbot): broadcast desktop audio + smart subtitles in the browse scenario

Two broadcast-experience improvements:

- Audio: the Go-Live stream was video-only. Capture the desktop sound (the
  default PipeWire/Pulse sink monitor, @DEFAULT_MONITOR@) as a second ffmpeg
  input and mux AAC into the mpegts; the library re-encodes it to Opus for
  Discord. Controlled by STREAM_AUDIO / STREAM_AUDIO_SOURCE (default on). ffmpeg
  inherits XDG_RUNTIME_DIR to reach the pulse socket. Verified: the streamer now
  reports "Found audio stream" and the monitor carries Chrome audio (~-11 dB).
- Subtitles: in the browse scenario, default captions OFF, but auto-enable a
  Korean track when the video offers one (getOption captions tracklist ->
  setOption / unloadModule).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.env.example

@@ -78,6 +78,11 @@ DISCORD_SELFBOT_TOKEN=
 # Hardware (NVENC) encode for the stream. 1 = use the GPU (recommended for
 # 1080p60), 0 = software x264. Requires an NVIDIA GPU + ffmpeg built with nvenc.
 STREAM_HW=1
+# Capture desktop audio into the broadcast so the stream has sound. 1 = on,
+# 0 = mute. Pulls the PipeWire/Pulse monitor of the default sink; override the
+# source with STREAM_AUDIO_SOURCE (e.g. a specific "<sink>.monitor").
+STREAM_AUDIO=1
+STREAM_AUDIO_SOURCE=@DEFAULT_MONITOR@
 
 # --- novnc backend ---
 # e.g. http://192.168.10.9:6080/vnc.html  (websockify --web=/usr/share/novnc 6080 localhost:5901)

bot/scripts/stream-test/scenario.mjs

@@ -43,6 +43,23 @@ async function browserFullscreen(on) {
   } catch { /* best-effort */ }
 }
 
+// Subtitles: OFF by default, but turn ON Korean when a Korean track exists.
+async function applyCaptions() {
+  await read(() => { try { document.getElementById('movie_player')?.loadModule?.('captions'); } catch {} });
+  await sleep(800);
+  return read(() => {
+    const pl = document.getElementById('movie_player');
+    if (!pl || !pl.getOption) return 'no-player';
+    let tracks = [];
+    try { tracks = pl.getOption('captions', 'tracklist') || []; } catch {}
+    const ko = tracks.find((t) => /^ko/i.test(t.languageCode || ''));
+    if (ko) { try { pl.setOption('captions', 'track', { languageCode: ko.languageCode }); } catch {} return 'ko-on'; }
+    try { pl.setOption('captions', 'track', {}); } catch {}
+    try { pl.unloadModule('captions'); } catch {}
+    return 'off';
+  });
+}
+
 // 1) open YouTube by typing the URL in the address bar
 await navigateOmnibox('https://www.youtube.com'); await sleep(3000);
 
@@ -84,6 +101,7 @@ async function setQuality1080() {
   return null;
 }
 console.log('QUALITY', await setQuality1080());
+console.log('CAPTIONS', await applyCaptions());
 
 // 6) turn off autoplay with a real click if it is on
 const auto = page.locator('.ytp-autonav-toggle-button');

bot/scripts/stream-test/stream-hold.ts

@@ -18,6 +18,8 @@ const config = {
   vncFramerate: parseInt(process.env.VNC_FRAMERATE ?? "60", 10),
   vncBitrateKbps: parseInt(process.env.VNC_BITRATE_KBPS ?? "8000", 10),
   streamHw: (process.env.STREAM_HW ?? "1") !== "0",
+  streamAudio: (process.env.STREAM_AUDIO ?? "1") !== "0",
+  streamAudioSource: process.env.STREAM_AUDIO_SOURCE ?? "@DEFAULT_MONITOR@",
 } as any;
 
 const guildId = process.env.DISCORD_GUILD_ID;

bot/src/config.ts

@@ -42,6 +42,11 @@ export const config = {
   selfbotToken: opt("DISCORD_SELFBOT_TOKEN"),
   // Use NVENC hardware encode + hw-accelerated decode for the stream (RTX 5050).
   streamHw: opt("STREAM_HW", "1") !== "0",
+  // Capture desktop audio into the broadcast so the stream has sound. Pulls the
+  // PipeWire/Pulse monitor of the default sink (what the desktop plays). Set
+  // STREAM_AUDIO=0 to mute; STREAM_AUDIO_SOURCE overrides the capture source.
+  streamAudio: opt("STREAM_AUDIO", "1") !== "0",
+  streamAudioSource: opt("STREAM_AUDIO_SOURCE", "@DEFAULT_MONITOR@"),
 
   // novnc backend
   novncUrl: opt("NOVNC_URL", ""),

bot/src/stream/selfbot.ts

@@ -143,17 +143,31 @@ export class SelfbotStreamer implements ScreenStreamer {
       const captureCodecArgs = hw
         ? ["-c:v", "h264_nvenc", "-preset", "p4", "-tune", "ll", "-forced-idr", "1"]
         : ["-c:v", "libx264", "-preset", "ultrafast", "-tune", "zerolatency"];
+      // Optionally pull desktop audio (the default sink's PipeWire/Pulse monitor)
+      // so the broadcast has sound. We add it as a second input and mux AAC into
+      // the mpegts; the library re-encodes it to Opus for Discord. ffmpeg needs
+      // XDG_RUNTIME_DIR (inherited) to reach the pulse socket. -map is required
+      // once there are two inputs.
+      const audioOn = this.config.streamAudio;
+      const audioInput = audioOn ? ["-f", "pulse", "-i", this.config.streamAudioSource] : [];
+      const audioMap = audioOn ? ["-map", "0:v:0", "-map", "1:a:0"] : [];
+      const audioCodec = audioOn ? ["-c:a", "aac", "-b:a", "160k", "-ar", "48000", "-ac", "2"] : [];
       capture = this.capture = spawn("ffmpeg", [
         "-loglevel", "error",
+        "-thread_queue_size", "1024",
         "-f", "x11grab",
         "-framerate", String(this.config.vncFramerate),
         "-video_size", this.config.vncResolution,
         "-i", this.config.vncDisplay,
+        ...(audioOn ? ["-thread_queue_size", "1024"] : []),
+        ...audioInput,
+        ...audioMap,
         ...captureCodecArgs,
         "-b:v", `${kbps}k`, "-maxrate", `${maxKbps}k`, "-bufsize", `${kbps}k`,
         "-bf", "0",
         "-pix_fmt", "yuv420p",
         "-g", String(this.config.vncFramerate),
+        ...audioCodec,
         "-f", "mpegts", "pipe:1",
       ]);
       capture.stderr?.on("data", (d) => {