Skip to main content
Use POST /v1/audio/translations when you want uploaded speech converted into English text. This endpoint is similar to transcription, but the returned text is translated English output rather than a same-language transcript.

​
Required and optional fields

FieldRequiredNotes
modelYesTranslation model
fileYesBinary audio upload
promptNoOptional formatting or name-preservation hint
languageNoOptional language 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",
)

translation = client.audio.translations.create(
    model="whisper-1",
    file=Path("spanish-interview.mp3"),
    prompt="Preserve product names exactly as spoken.",
)

print(translation.text)

​
Response Shape

{
  "text": "The speaker says the launch will happen next week."
}

​
When to use translation vs transcription

  • use translation when you want English text output from non-English audio
  • use Speech to Text when you want a same-language transcript

​
Common mistakes

  • expecting the output language to match the source audio
  • forgetting multipart form encoding
  • using the wrong endpoint when a transcript would be enough

​
Reference