Image inputs in the GPT-4 API

API
1

I saw the announcement here - Image inputs for ChatGPT - FAQ | OpenAI Help Center

Image inputs are being rolled out in ChatGPT (Plus and Enterprise).

Still image inputs are not being rolled out in the API (https://platform.openai.com/), is that correct?

2 Likes
2

Ditto to this but for the Voice recognition, really want to use the voice conversation feature in my app

1 Like
3

“We’re rolling out voice and images in ChatGPT to Plus and Enterprise users over the next two weeks. Voice is coming on iOS and Android (opt-in in your settings) and images will be available on all platforms.”

edit: wrong section was copy and pasted, here is what was ment to be posted: “Plus and Enterprise users will get to experience voice and images in the next two weeks. We’re excited to roll out these capabilities to other groups of users, including developers, soon after.”

1 Like
5

that doesn’t help answer anything on the API release

3 Likes
6

Voice transcription features can be implemented by using the Whisper API.

You can monitor these official announcements, found on the OpenAI blog, Twitter, and Discord, and update us.

There are no insiders spilling unannounced information here.

2 Likes
7

Ah just re read what was copied and pasted, hang on.

8

“Plus and Enterprise users will get to experience voice and images in the next two weeks. We’re excited to roll out these capabilities to other groups of users, including developers, soon after.”

5 Likes
9

Yes, I think that answers the question.

2 Likes
10

hi, when will it be? 15 days have already passed

2 Likes
11

It will be announced on this forum, social media and the OpenAI Blog when it becomes available, for now, please be patient.

2 Likes
12

Hi guys! Can you please provide any updates on when approximately developers API will be rolled out?

1 Like
13

Just came out with the preview version for API: New models and developer products announced at DevDay

Prod version hopefully soon

1 Like
14

The example code for inputting images can be found in the API Reference documentation：
POST https://api.openai.com/v1/chat/completions

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="gpt-4-vision-preview",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What’s in this image?"},
                {
                    "type": "image_url",
                    "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
                },
            ],
        }
    ],
    max_tokens=300,
)

print(response.choices[0])