Skip to main content
Use POST /v1/audio/transcriptions when you want a same-language text transcript of uploaded audio. This endpoint accepts multipart form uploads and returns one JSON response with a text field.

​
Required and optional fields

FieldRequiredNotes
modelYesTranscription model
fileYesBinary audio upload
languageNoOptional language hint
promptNoOptional formatting or name-preservation hint

​
Multipart Request Example

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    base_url="https://api.naga.ac/v1",
    api_key="YOUR_API_KEY",
)

transcription = client.audio.transcriptions.create(
    model="whisper-1",
    file=Path("meeting.mp3"),
    language="en",
    prompt="Preserve product names exactly as spoken.",
)

print(transcription.text)

​
Response Shape

{
  "text": "Welcome to the weekly engineering update..."
}

​
When to use transcription vs translation

  • use transcription when you want text in the same language as the audio
  • use Speech Translation when you want translated English text

​
Common Mistakes

  • uploading a corrupted or unsupported audio file
  • forgetting multipart form encoding
  • assuming the response is a streamed token feed rather than one final JSON object

​
Reference