Update Realtime Prompting Guide for clarity and consistency

- Revised text to enhance clarity, including changes to descriptions of the gpt-realtime model and its capabilities.
- Updated audio file references to reflect the new gpt-realtime model.
- Improved formatting and added additional context for better understanding of prompting techniques.

Author: minh-hoque

examples/Realtime_prompting_guide.ipynb

@@ -15,12 +15,12 @@
     "\n",
     "Today, we’re releasing gpt-realtime — our most capable speech-to-speech model yet in the API and announcing the general availability of the Realtime API. \n",
     "\n",
-    "Speech-to-speech systems are essential for enabling voice as a core AI interface. Today’s release enhances robustness and usability, giving enterprises the confidence to deploy mission-critical voice agents at scale.\n",
+    "Speech-to-speech systems are essential for enabling voice as a core AI interface. The new release enhances robustness and usability, giving enterprises the confidence to deploy mission-critical voice agents at scale.\n",
     "\n",
     "\n",
-    "The new gpt-realtime model delivers stronger instruction following, more reliable tool calling, noticeably better voice quality, and an overall smoother feel. These gains make it practical to move from chained approaches to true realtime experiences, cutting latency, carrying over more nuance from spoken input, and producing responses that sound more natural and expressive.\n",
+    "The new gpt-realtime model delivers stronger instruction following, more reliable tool calling, noticeably better voice quality, and an overall smoother feel. These gains make it practical to move from chained approaches to true realtime experiences, cutting latency and producing responses that sound more natural and expressive.\n",
     "\n",
-    "Realtime model benefit from different prompting techniques that wouldn't directly apply to text based models. This prompting guide starts with a simple prompt skeleton, then walks through each part with practical tips, small patterns you can copy, and examples you can adapt to your use case.\n",
+    "Realtime model benefit from different prompting techniques that wouldn't directly apply to text based models. This prompting guide starts with a suggested prompt skeleton, then walks through each part with practical tips, small patterns you can copy, and examples you can adapt to your use case.\n",
     "\n",
     "# Table of Contents\n",
     "\n",
@@ -185,7 +185,7 @@
    "id": "d36c87e3",
    "metadata": {},
    "source": [
-    "This is the audio from our new GA model `gpt-4o-realtime-preview-2025-08-29`"
+    "This is the audio from our new GA model `gpt-realtime`"
    ]
   },
   {
@@ -271,7 +271,7 @@
    "id": "084f7cae",
    "metadata": {},
    "source": [
-    "This is the audio from our new GA model `gpt-4o-realtime-preview-2025-08-29`"
+    "This is the audio from our new GA model `gpt-realtime`"
    ]
   },
   {
@@ -354,7 +354,9 @@
     "- Start your response very happy\n",
     "- Midway, change to sad\n",
     "- At the end change your mood to very angry\n",
-    "```"
+    "```\n",
+    "\n",
+    "This is the audio from our new GA model `gpt-realtime`"
    ]
   },
   {
@@ -435,7 +437,7 @@
    "id": "da1ac60b",
    "metadata": {},
    "source": [
-    "This is the audio from our old `gpt-4o-realtime-preview-2025-06-03`"
+    "This is the audio from our old `gpt-4o-realtime-preview-2025-06-03` with speed instructions"
    ]
   },
   {
@@ -472,7 +474,7 @@
    "id": "77cd87ce",
    "metadata": {},
    "source": [
-    "This is the audio from our new GA model `gpt-4o-realtime-preview-2025-08-29` after adding the instruction to the same prompt."
+    "This is the audio from our new GA model `gpt-realtime` with speed instructions"
    ]
   },
   {
@@ -553,7 +555,7 @@
    "id": "4dd0c9bf",
    "metadata": {},
    "source": [
-    "This is the responses after applying the instruction using `gpt-4o-realtime-preview-2025-08-29`\n",
+    "This is the responses after applying the instruction using `gpt-realtime`\n",
     "\n",
     "<img\n",
     "  src=\"../images/lang_constraint_en.png\"\n",
@@ -598,7 +600,7 @@
    "id": "891519ed",
    "metadata": {},
    "source": [
-    "This is the responses after applying the instruction using `gpt-4o-realtime-preview-2025-08-29`\n",
+    "This is the responses after applying the instruction using `gpt-realtime`\n",
     "\n",
     "\n",
     "<img\n",
@@ -655,7 +657,7 @@
    "id": "7d0da635",
    "metadata": {},
    "source": [
-    "This is the responses **before** applying the instruction using `gpt-4o-realtime-preview-2025-08-29`\n",
+    "This is the responses **before** applying the instruction using `gpt-realtime`\n",
     "\n",
     "<img\n",
     "  src=\"../images/repeat_before.png\"\n",
@@ -668,7 +670,7 @@
    "id": "84fc575c",
    "metadata": {},
    "source": [
-    "This is the responses **after** applying the instruction using `gpt-4o-realtime-preview-2025-08-29`\n",
+    "This is the responses **after** applying the instruction using `gpt-realtime`\n",
     "\n",
     "\n",
     "<img\n",
@@ -752,7 +754,7 @@
    "id": "93f9b8b5",
    "metadata": {},
    "source": [
-    "This is the audio from our new GA model `gpt-4o-realtime-preview-2025-08-29` using the reference pronunciations.\n",
+    "This is the audio from our new GA model `gpt-realtime` using the reference pronunciations.\n",
     "\n",
     "It is able to correctly pronounce SQL as \"sequel\"."
    ]
@@ -848,7 +850,7 @@
    "id": "43f9826e",
    "metadata": {},
    "source": [
-    "This is the responses **before** applying the instruction using `gpt-4o-realtime-preview-2025-08-29`\n",
+    "This is the responses **before** applying the instruction using `gpt-realtime`\n",
     "\n",
     "> Sure! The number is 55119765423. Let me know if you need anything else!"
    ]
@@ -858,7 +860,7 @@
    "id": "54a62295",
    "metadata": {},
    "source": [
-    "This is the responses **after** applying the instruction using `gpt-4o-realtime-preview-2025-08-29`\n",
+    "This is the responses **after** applying the instruction using `gpt-realtime`\n",
     "\n",
     "> Sure! The number is: 5-5-1-1-1-9-7-6-5-4-2-3. Please let me know if you need anything else!"
    ]
@@ -956,7 +958,9 @@
     "- Always respond in the same language the user is speaking in, if intelligible.\n",
     "- Only respond to clear audio or text. \n",
     "- If the user's audio is not clear (e.g. ambiguous input/background noise/silent/unintelligible) or if you did not fully hear or understand the user, ask for clarification using {preferred_language} phrases.\n",
-    "```"
+    "```\n",
+    "\n",
+    "This is the responses **after** applying the instruction using `gpt-realtime`"
    ]
   },
   {
@@ -1083,7 +1087,7 @@
    "id": "e8839685",
    "metadata": {},
    "source": [
-    "This is the responses after applying the instruction using `gpt-4o-realtime-preview-2025-08-29`\n",
+    "This is the responses after applying the instruction using `gpt-realtime`\n",
     "\n",
     "<img\n",
     "  src=\"../images/tool_proactive.png\"\n",
@@ -1170,7 +1174,7 @@
    "id": "672cb487",
    "metadata": {},
    "source": [
-    "This is the responses **after** applying the instruction using `gpt-4o-realtime-preview-2025-08-29`\n",
+    "This is the responses **after** applying the instruction using `gpt-realtime`\n",
     "\n",
     "<img\n",
     "  src=\"../images/tool_no_confirm.png\"\n",
@@ -1358,7 +1362,7 @@
    "id": "7d30e0d5",
    "metadata": {},
    "source": [
-    "Here’s an example without rephrasing instruction:\n",
+    "Here’s an example without the rephrasing instruction:\n",
     "\n",
     ">Assistant: Your current credit card balance is positive at 32,323,232 AUD."
    ]
@@ -1368,7 +1372,7 @@
    "id": "91f73021",
    "metadata": {},
    "source": [
-    "Here’s the same example with rephrasing instruction:\n",
+    "Here’s the same example with the rephrasing instruction:\n",
     "\n",
     ">Assistant: Just finished checking that—your credit card balance is thirty-two million three hundred twenty-three thousand two hundred thirty-two dollars in your favor. Your last payment was processed on August first. Does that match what you expected?"
    ]
@@ -1484,6 +1488,7 @@
    "metadata": {},
    "source": [
     "## Sample phrases\n",
+    "Sample phrases act as “anchor examples” for the model. They show the style, brevity, and tone you want it to follow, without locking it into one rigid response.\n",
     "\n",
     "- **When to use**: Responses lack your brand style or are not consistent.\n",
     "- **What it does**: Provides sample phrases the model can vary to stay natural and brief.\n",
@@ -1874,7 +1879,7 @@
    "id": "860fdb2e",
    "metadata": {},
    "source": [
-    "This is the conversation responses from our new GA model `gpt-4o-realtime-preview-2025-08-29` using the instruction.\n",
+    "This is the conversation responses from our new GA model `gpt-realtime` using the instruction.\n",
     "\n",
     "<img\n",
     "  src=\"../images/escalate_07.png\"\n",