语音转写与翻译

import os
import sys
from pathlib import Path
from openai import OpenAI, APIConnectionError, APIStatusError

mode = sys.argv[1] if len(sys.argv) == 2 else ""
if mode not in ("transcribe", "translate"):
    raise SystemExit("Usage: python transcribe.py transcribe|translate")
source = Path(os.environ["API_AUDIO_PATH"])
# A local example limit, not a universal provider upload limit.
if not 0 < source.stat().st_size <= 20 * 1024 * 1024:
    raise SystemExit("Choose a nonempty recording up to 20 MiB for this example.")

with OpenAI(base_url=os.environ["API_BASE_URL"].rstrip("/"),
            api_key=os.environ["API_KEY"], timeout=120.0, max_retries=0) as client:
    try:
        endpoint = client.audio.transcriptions if mode == "transcribe" else client.audio.translations
        with source.open("rb") as recording:
            result = endpoint.create(model=os.environ["API_MODEL"], file=recording, response_format="json")
        if not isinstance(result.text, str):
            raise ValueError("Expected a text field.")
        print(result.text)
    except APIStatusError as error:
        raise SystemExit(f"Request failed (HTTP {error.status_code}). Check the request logs.")
    except APIConnectionError:
        raise SystemExit("Connection failed. Check the API address and network.")
    except ValueError:
        raise SystemExit("Invalid transcription response; expected JSON with text.")