Skip to content

Commit 2bf9c1b

Browse files
authored
Update markdown headers in Realtime out-of-band transcription example… (#2252)
1 parent 22fda54 commit 2bf9c1b

File tree

1 file changed

+11
-9
lines changed

1 file changed

+11
-9
lines changed

examples/Realtime_out_of_band_transcription.ipynb

Lines changed: 11 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -38,9 +38,10 @@
3838
},
3939
{
4040
"cell_type": "markdown",
41+
"id": "1c0f46ad",
4142
"metadata": {},
4243
"source": [
43-
"## 1. Why use out-of-band transcription?\n",
44+
"# 1. Why use out-of-band transcription?\n",
4445
"\n",
4546
"The Realtime API offers built-in user input transcription, but this relies on a **separate ASR model** (e.g., gpt-4o-transcribe). Using different models for transcription and response generation can lead to discrepancies. For example:\n",
4647
"\n",
@@ -100,9 +101,10 @@
100101
},
101102
{
102103
"cell_type": "markdown",
104+
"id": "63ccae3d",
103105
"metadata": {},
104106
"source": [
105-
"## 2. Requirements & Setup\n",
107+
"# 2. Requirements & Setup\n",
106108
"\n",
107109
"Ensure your environment meets these requirements:\n",
108110
"\n",
@@ -144,7 +146,7 @@
144146
"id": "d7d60089",
145147
"metadata": {},
146148
"source": [
147-
"## 3. Prompts\n",
149+
"# 3. Prompts\n",
148150
"\n",
149151
"We use **two distinct prompts**:\n",
150152
"\n",
@@ -201,7 +203,7 @@
201203
"id": "4ddbd683",
202204
"metadata": {},
203205
"source": [
204-
"## 4. Core configuration\n",
206+
"# 4. Core configuration\n",
205207
"\n",
206208
"We define:\n",
207209
"\n",
@@ -291,7 +293,7 @@
291293
"id": "a905ec16",
292294
"metadata": {},
293295
"source": [
294-
"## 5. Building the Realtime session & the out‑of‑band request\n",
296+
"# 5. Building the Realtime session & the out‑of‑band request\n",
295297
"\n",
296298
"The Realtime session (`session.update`) configures:\n",
297299
"\n",
@@ -394,7 +396,7 @@
394396
"id": "9afe7911",
395397
"metadata": {},
396398
"source": [
397-
"## 6. Audio streaming: mic → Realtime → speakers\n",
399+
"# 6. Audio streaming: mic → Realtime → speakers\n",
398400
"\n",
399401
"We now define:\n",
400402
"\n",
@@ -506,7 +508,7 @@
506508
"id": "d02cc1bd",
507509
"metadata": {},
508510
"source": [
509-
"## 7. Extracting and comparing transcripts\n",
511+
"# 7. Extracting and comparing transcripts\n",
510512
"\n",
511513
"The function below enables us to generate **two transcripts** for each user turn:\n",
512514
"\n",
@@ -556,7 +558,7 @@
556558
"id": "6025bbf6",
557559
"metadata": {},
558560
"source": [
559-
"## 8. Listening for Realtime events\n",
561+
"# 8. Listening for Realtime events\n",
560562
"\n",
561563
"`listen_for_events` drives the session:\n",
562564
"\n",
@@ -739,7 +741,7 @@
739741
"id": "10c69ded",
740742
"metadata": {},
741743
"source": [
742-
"## 9. Run Script\n",
744+
"# 9. Run Script\n",
743745
"\n",
744746
"In this step, we run the the code which will allow us to view the realtime model transcription vs transcription model transcriptions. The code does the following:\n",
745747
"\n",

0 commit comments

Comments
 (0)