語音轉寫與播報

import os
from openai import OpenAI

client = OpenAI(base_url="https://www.tutujin.com/v1", api_key=os.environ["TUTUJIN_API_KEY"])

# 1. speech to text: split long recordings into 10 to 20 minute files first
with open("meeting-part1.mp3", "rb") as f:
    transcript = client.audio.transcriptions.create(model="whisper-1", file=f, language="zh")

# 2. turn the transcript into minutes
minutes = client.chat.completions.create(
    model="qwen3.5-plus",
    messages=[
        {"role": "system", "content": "Write meeting minutes: decisions, action items with owner and due date, open questions. Under 300 words."},
        {"role": "user", "content": transcript.text},
    ],
).choices[0].message.content
print(minutes)

# 3. read a notice aloud (available voices depend on the model)
with client.audio.speech.with_streaming_response.create(
    model="tts-1",
    voice="alloy",
    input="The minutes of today's meeting have been sent to your inbox.",
) as resp:
    resp.stream_to_file("notice.mp3")