Update Realtime Prompting Guide with formatting improvements and execution count adjustments

- Added bullet points for personality and tone descriptions for better readability.
- Updated execution counts in code cells for consistency.
- Revised audio file paths to ensure correct referencing.
- Enhanced clarity in instructional examples and tips throughout the guide.

Author: minh-hoque

examples/Realtime_prompting_guide.ipynb

@@ -334,10 +334,10 @@
     "```\n",
     "# Personality & Tone\n",
     "## Personality\n",
-    "Friendly, calm and approachable expert customer service assistant.\n",
+    "- Friendly, calm and approachable expert customer service assistant.\n",
     "\n",
     "## Tone\n",
-    "Warm, concise, confident, never fawning.\n",
+    "- Warm, concise, confident, never fawning.\n",
     "\n",
     "## Length\n",
     "2–3 sentences per turn.\n",
@@ -362,7 +362,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "6dce17d5",
    "metadata": {},
    "outputs": [
@@ -380,13 +380,13 @@
        "<IPython.lib.display.Audio object>"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "Audio(\"/Users/minh.hoque/work/github/openai-cookbook/examples/data/audio/multi-emotion.wav\")"
+    "Audio(\"./data/audio/multi-emotion.wav\")"
    ]
   },
   {
@@ -419,13 +419,13 @@
     "```\n",
     "# Personality & Tone\n",
     "## Personality\n",
-    "Friendly, calm and approachable expert customer service assistant.\n",
+    "- Friendly, calm and approachable expert customer service assistant.\n",
     "\n",
     "## Tone\n",
-    "Warm, concise, confident, never fawning.\n",
+    "- Warm, concise, confident, never fawning.\n",
     "\n",
     "## Length\n",
-    "2–3 sentences per turn.\n",
+    "- 2–3 sentences per turn.\n",
     "\n",
     "## Pacing\n",
     "- Deliver your audio response fast, but do not sound rushed.\n",
@@ -537,13 +537,13 @@
     "```\n",
     "# Personality & Tone\n",
     "## Personality\n",
-    "Friendly, calm and approachable expert customer service assistant.\n",
+    "- Friendly, calm and approachable expert customer service assistant.\n",
     "\n",
     "## Tone\n",
-    "Warm, concise, confident, never fawning.\n",
+    "- Warm, concise, confident, never fawning.\n",
     "\n",
     "## Length\n",
-    "2–3 sentences per turn.\n",
+    "- 2–3 sentences per turn.\n",
     "\n",
     "## Language\n",
     "- The conversation will be only in English.\n",
@@ -574,19 +574,19 @@
     "### Example (model teaches a language)\n",
     "```\n",
     "# Role & Objective\n",
-    "You are a friendly, knowledgeable voice tutor for French learners.  \n",
-    "Your goal is to help the user improve their French speaking and listening skills through engaging conversation and clear explanations.  \n",
-    "Balance immersive French practice with supportive English guidance to ensure understanding and progress.\n",
+    "- You are a friendly, knowledgeable voice tutor for French learners.  \n",
+    "- Your goal is to help the user improve their French speaking and listening skills through engaging conversation and clear explanations.  \n",
+    "- Balance immersive French practice with supportive English guidance to ensure understanding and progress.\n",
     "\n",
     "# Personality & Tone\n",
     "## Personality\n",
-    "Friendly, calm and approachable expert voice tutor.\n",
+    "- Friendly, calm and approachable expert customer service assistant.\n",
     "\n",
     "## Tone\n",
-    "Warm, concise, confident, never fawning.\n",
+    "- Warm, concise, confident, never fawning.\n",
     "\n",
     "## Length\n",
-    "2–3 sentences per turn.\n",
+    "- 2–3 sentences per turn.\n",
     "\n",
     "## Language\n",
     "### Explanations\n",
@@ -635,13 +635,13 @@
     "```\n",
     "# Personality & Tone\n",
     "## Personality\n",
-    "Friendly, calm and approachable expert customer service assistant.\n",
+    "- Friendly, calm and approachable expert customer service assistant.\n",
     "\n",
     "## Tone\n",
-    "Warm, concise, confident, never fawning.\n",
+    "- Warm, concise, confident, never fawning.\n",
     "\n",
     "## Length\n",
-    "2–3 sentences per turn.\n",
+    "- 2–3 sentences per turn.\n",
     "\n",
     "## Language\n",
     "- The conversation will be only in English.\n",
@@ -807,7 +807,7 @@
    "id": "60708efd",
    "metadata": {},
    "source": [
-    "### Example\n",
+    "### Example (general instruction section)\n",
     "```\n",
     "# Instructions/Rules\n",
     "- When reading numbers or codes, speak each character separately, separated by hyphens (e.g., 4-1-5). \n",
@@ -822,7 +822,7 @@
    "source": [
     "*Tip: If you are following a conversation flow prompting strategy, you can specify which conversation state needs to apply the alpha-numeric pronunciations instruction.*\n",
     "\n",
-    "### Example \n",
+    "### Example (instruction in conversation state)\n",
     "*(taken from the conversation flow of the prompt of our [openai-realtime-agents](https://github.com/openai/openai-realtime-agents/blob/main/src/app/agentConfigs/customerServiceRetail/authentication.ts))*\n",
     "\n",
     "```txt\n",
@@ -1214,7 +1214,7 @@
    "id": "30ccc1d9",
    "metadata": {},
    "source": [
-    "*Tip: If a tool call can fail unpredictably, add clear failure-handling instructions so the model responds gracefully.*"
+    "*Tip: If you notice the model is jumping too quickly to call a tool, try softening the wording. For example, swapping out stronger terms like “proactive” with something gentler can help guide the model to take a calmer, less eager approach.*"
    ]
   },
   {
@@ -1269,7 +1269,7 @@
    "id": "24579f54",
    "metadata": {},
    "source": [
-    "*Tip: If your tool call can fail in unpredictablr ways, try adding instructions on how to handle tool call outputs failures so taht the model can behave*"
+    "*Tip: If a tool call can fail unpredictably, add clear failure-handling instructions so the model responds gracefully.*"
    ]
   },
   {