There is no metadata, please fix it

[kopyl]

Describe the bug

There is no metadata in the response for individual words like what's the language of a word, start time and end time.

To Reproduce

1. Run the code snippet below.

Code snippets

os
import openai

openai.organization = os.environ.get("OPENAIORGANIZATIONID")
openai.api_key = os.environ.get("OPENAIAPIKEY")

file = open("/Users/olehkopyl/Downloads/test.m4a", "rb")
transcription = openai.Audio.transcribe("whisper-1", file)

print(transcription)

OS

macOS

Python version

3.8.13

Library version

0.27.0

[mpokrass]

hi there! we do offer a different response format for whisper if you want to get more verbose data about the audio. you can try it out like so

import openai
f = open("/path/to/file.mp3", "rb")
transcript = openai.Audio.transcribe("whisper-1", f, response_format="verbose_json")

[kopyl]

@mpokrass nope,

1. It only transcribes in one language
2. It does not tell a language for each token/segment

Any way to make it actually work?