transcribe mp3 to text api

If you want to transcribe an MP3 to text via API, the common options are:

1) OpenAI transcription API

You upload the audio file and get back text.

Python example

from openai import OpenAI

client = OpenAI()

with open("audio.mp3", "rb") as f:
    transcript = client.audio.transcriptions.create(
        model="gpt-4o-mini-transcribe",
        file=f
    )

print(transcript.text)

cURL example

curl https://api.openai.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file="@audio.mp3" \
  -F model="gpt-4o-mini-transcribe"

2) Whisper-style API workflow

If your provider supports Whisper-compatible endpoints, the pattern is usually:

• multipart/form-data
• upload the MP3 file
• specify transcription model
• receive plain text or JSON

Notes

• MP3 is supported by most transcription APIs.
• If you need timestamps, speaker diarization, or language detection, check whether the API supports those options.
• For large files, you may need to split audio into chunks.

If you want, I can give you:

• Node.js example
• FastAPI backend example
• React upload + transcription flow
• a working OpenAI API request for timestamps