Audio

Author: AntonioMonzo4

OPENIA/audios.py

@@ -0,0 +1,64 @@
+#AUDIO OUTPUT 
+import base64
+from openai import OpenAI
+
+client = OpenAI()
+
+completion = client.chat.completions.create(
+    model="gpt-audio",
+    modalities=["text", "audio"],
+    audio={"voice": "alloy", "format": "wav"},
+    messages=[
+        {
+            "role": "user",
+            "content": "Is a golden retriever a good family dog?"
+        }
+    ]
+)
+
+print(completion.choices[0])
+
+wav_bytes = base64.b64decode(completion.choices[0].message.audio.data)
+with open("dog.wav", "wb") as f:
+    f.write(wav_bytes)
+
+#AUDIO INPUT 
+
+import base64
+import requests
+from openai import OpenAI
+
+client = OpenAI()
+
+# Fetch the audio file and convert it to a base64 encoded string
+url = "https://cdn.openai.com/API/docs/audio/alloy.wav"
+response = requests.get(url)
+response.raise_for_status()
+wav_data = response.content
+encoded_string = base64.b64encode(wav_data).decode('utf-8')
+
+completion = client.chat.completions.create(
+    model="gpt-audio",
+    modalities=["text", "audio"],
+    audio={"voice": "alloy", "format": "wav"},
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                { 
+                    "type": "text",
+                    "text": "What is in this recording?"
+                },
+                {
+                    "type": "input_audio",
+                    "input_audio": {
+                        "data": encoded_string,
+                        "format": "wav"
+                    }
+                }
+            ]
+        },
+    ]
+)
+
+print(completion.choices[0].message)

OPENIA/crear_img.py

@@ -19,4 +19,30 @@
 if image_data:
     image_base64 = image_data[0]
     with open("cat_and_otter.png", "wb") as f:
-        f.write(base64.b64decode(image_base64))
+        f.write(base64.b64decode(image_base64))
+
+
+
+
+#OPCIÓN 2 
+
+from openai import OpenAI
+import base64
+client = OpenAI()
+
+prompt = """
+A children's book drawing of a veterinarian using a stethoscope to 
+listen to the heartbeat of a baby otter.
+"""
+
+result = client.images.generate(
+    model="gpt-image-2",
+    prompt=prompt
+)
+
+image_base64 = result.data[0].b64_json
+image_bytes = base64.b64decode(image_base64)
+
+# Save the image to a file
+with open("otter.png", "wb") as f:
+    f.write(image_bytes)

OPENIA/vision.py

@@ -0,0 +1,19 @@
+from openai import OpenAI
+
+client = OpenAI()
+
+response = client.responses.create(
+    model="gpt-4.1-mini",
+    input=[{
+        "role": "user",
+        "content": [
+            {"type": "input_text", "text": "what's in this image?"},
+            {
+                "type": "input_image",
+                "image_url": "https://api.nga.gov/iiif/a2e6da57-3cd1-4235-b20e-95dcaefed6c8/full/!800,800/0/default.jpg",
+            },
+        ],
+    }],
+)
+
+print(response.output_text)