Is whisper not working on the API?

API
1

Anyone with this issue? It stopped working for me a about 10 minutes ago…

I’m curious if other members are having the same issue, on openai status it doesn’t have a report that the API is having an issue

2

have been using it all day till now, so no

3

What error did you receive from the API? I haven’t received any notification but still I suggest you always check https://status.openai.com/ and subscribe to their notifications

4

Today the end-point listed in the docs gives a 404 error. Subsequently the API endpoint on Groq is giving a 520 bad Gateway like it was moved, but the documentation still lists the same URL. What’s going on with all the whispers? Lol

5

It’s working.

HEADERS = {'Authorization': f'Bearer {API_KEY}'}
ENDPOINT = "https://api.openai.com/v1/audio/transcriptions"

Python code using endpoint and httpx module to upload and save 
import httpx
import os

API_KEY = os.getenv('OPENAI_API_KEY')
HEADERS = {'Authorization': f'Bearer {API_KEY}'}
ENDPOINT = "https://api.openai.com/v1/audio/transcriptions"

input_file_path = "audio.mp3"
output_file_path = input_file_path + "-transcript.txt"

def transcribe_audio(input_path: str, output_path: str) -> None:
    # Prepare the file for upload
    with open(input_path, 'rb') as file:
        files = {'file': (input_path, file, 'audio/mpeg')}
        data = {
            'model': 'whisper-1',
            'language': 'en',
            'prompt': 'Hello, and welcome to our talk.',
            'response_format': 'json'
        }

        # Adjust the timeout settings for the request
        timeout = httpx.Timeout(600.0, connect=120.0)

        # Make the API request
        try:
            with httpx.Client(timeout=timeout) as client:
                response = client.post(ENDPOINT, headers=HEADERS, files=files, data=data)
                response.raise_for_status()  # Will raise an exception for HTTP error responses
                transcription = response.json()
        except httpx.ReadTimeout:
            print("The request timed out while waiting for the server to send data.")
            return
        except Exception as e:
            print(f"API request failed: {e}")
            return

        # Extract the text from the JSON response
        transcribed_text = transcription.get('text', '')

        # Save the transcribed text to a file
        try:
            with open(output_path, "w") as out_file:
                out_file.write(transcribed_text)
            print(f"--- Transcribed text successfully saved to '{output_path}'.")
        except Exception as e:
            print(f"Error writing to output file: {e}")

        # Optionally print an excerpt of the transcript
        print(elide_text(transcribed_text))

def elide_text(text: str, start: int = 240, end: int = 240, ellipsis: str = '\n...\n') -> str:
    if len(text) <= start + end:
        return text
    return text[:start] + ellipsis + text[-end:]

# Call the function to transcribe audio
transcribe_audio(input_file_path, output_file_path)
6

Weird. I am still getting 404 back with your script. Maybe this is DNS propagation related.

7

a couple of hours after I had that issue in May, it started working again