语音识别 STT（Audio Transcriptions）

curl https://open.tutujin.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $TUTUJIN_API_KEY" \
  -F file=@meeting.mp3 \
  -F model="whisper-1" \
  -F language=zh \
  -F prompt="土土金，季度复盘，客户成功"

import os
from openai import OpenAI

client = OpenAI(base_url="https://open.tutujin.com/v1", api_key=os.environ["TUTUJIN_API_KEY"], timeout=300)

with open("meeting.mp3", "rb") as f:
    result = client.audio.transcriptions.create(
        model="whisper-1",
        file=f,
        language="zh",
        prompt="土土金，季度复盘，客户成功",
    )
print(result.text)

import fs from 'node:fs'
import OpenAI from 'openai'

const client = new OpenAI({ baseURL: 'https://open.tutujin.com/v1', apiKey: process.env.TUTUJIN_API_KEY, timeout: 300_000 })

const result = await client.audio.transcriptions.create({
  model: 'whisper-1',
  file: fs.createReadStream('meeting.mp3'),
  language: 'zh',
  prompt: '土土金，季度复盘，客户成功',
})
console.log(result.text)

{
  "text": "我们先回顾一下这个季度的客户成功指标……"
}

1
00:00:00,000 --> 00:00:03,200
我们先回顾一下这个季度的客户成功指标

2
00:00:03,200 --> 00:00:06,900
整体续约率比上季度有所提升