Create translation
Some speech-capable models can translate spoken audio into English. Replace YOUR_SPEECH_MODEL_ID with a model ID that the current catalog marks as supporting audio translation:
from openai import OpenAI client = OpenAI( base_url="https://api.livrouter.com/v1") with open("audio.mp3", "rb") as audio_file: transcription = client.audio.translations.create( model="YOUR_SPEECH_MODEL_ID", file=audio_file ) print(transcription.text)