Improved markdown table

Author: minh-hoque

examples/Speech_transcription_methods.ipynb

@@ -19,12 +19,12 @@
    "metadata": {},
    "source": [
     "### 📊 Quick-look\n",
-    "| Mode                           | Latency to **first token** | Best for (real examples)                                     | What you still need to handle / key limits                |\n",
-    "|--------------------------------|-------------------------|--------------------------------------------------------------|-----------------------------------------------------------|\n",
-    "| File upload + `stream=False` (blocking)         | seconds                 | Voicemail, meeting recordings          | • No partial results, users see nothing until file finishes <br>• Max 25 MB per request (you must chunk long audio) |\n",
-    "| File upload + `stream=True`    | subseconds                  | Voice memos in mobile apps     | • Still requires a completed file <br>• You implement progress bars / chunked uploads |\n",
-    "| Realtime WebSocket             | subseconds                 | Live captions in webinars | • Audio must be pcm16, g711_ulaw, or g711_alaw <br>• Session ≤ 30 min, reconnect & stitch <br>• You handle speaker-turn formatting to build the full transcript |\n",
-    "| Agents SDK VoicePipeline       | subseconds                 | Internal help-desk assistant   | • Python-only beta <br>• API surface may change |"
+    "| Mode                           | Latency to **first token** | Best for (real examples)                                     | Advantages | What you still need to handle / key limits                |\n",
+    "|--------------------------------|---------------------------|--------------------------------------------------------------|-----------------------------------------------------------|-----------------------------------------------------------|\n",
+    "| File upload + `stream=False` (blocking) | seconds  | Voicemail, meeting recordings | Simple to set up | • No partial results, users see nothing until file finishes <br>• Max 25 MB per request (you must chunk long audio) |\n",
+    "| File upload + `stream=True`    | subseconds | Voice memos in mobile apps | Simple to set up & provides a “live” feel via token streaming | • Still requires a completed file <br>• You implement progress bars / chunked uploads |\n",
+    "| Realtime WebSocket             | subseconds | Live captions in webinars | True real-time; accepts a continuous audio stream | • Audio must be pcm16, g711_ulaw, or g711_alaw <br>• Session ≤ 30 min, reconnect & stitch <br>• You handle speaker-turn formatting to build the full transcript |\n",
+    "| Agents SDK VoicePipeline       | subseconds | Internal help-desk assistant | Real-time streaming and easy to build agentic workflows | • Python-only beta <br>• API surface may change |"
    ]
   },
   {
@@ -88,6 +88,7 @@
     "import os\n",
     "import time\n",
     "from typing import List\n",
+    "from pathlib import Path\n",
     "\n",
     "# ─── Third-Party ───────────────────────────────────────────────────────────────\n",
     "import nest_asyncio\n",
@@ -103,6 +104,7 @@
     "    VoicePipeline,\n",
     "    VoicePipelineConfig,\n",
     ")\n",
+    "from IPython.display import Audio, display\n",
     "# ───────────────────────────────────────────────────────────────────────────────\n",
     "nest_asyncio.apply()\n",
     "\n",
@@ -184,8 +186,6 @@
     }
    ],
    "source": [
-    "from IPython.display import Audio, display\n",
-    "from pathlib import Path\n",
     "AUDIO_PATH = Path('./data/sample_audio_files/lotsoftimes-78085.mp3')  # change me\n",
     "MODEL_NAME = \"gpt-4o-transcribe\"\n",
     "\n",
@@ -617,6 +617,13 @@
       "[User]: Like these next few links.\n",
       "[Assistant]: Comme ces quelques liens suivants."
      ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Error processing turns: no close frame received or sent\n"
+     ]
     }
    ],
    "source": [