OpenAI 음성 인식 API (/v1/audio/transcriptions)

curl -X POST 'https://api.acedata.cloud/v1/audio/transcriptions' \
  -H 'authorization: Bearer {token}' \
  -F file=@audio.mp3 \
  -F model=whisper-1

{
  "text": "Ace Data Cloud Platform is testing the speech recognition endpoint. The quick brown fox jumps over the lazy dog."
}

{
  "text": "欢迎使用 AceData Cloud 平台,我们正在测试语音识别接口,今天是 7 月 31 号。"
}

curl -X POST 'https://api.acedata.cloud/v1/audio/transcriptions' \
  -H 'authorization: Bearer {token}' \
  -F file=@audio.mp3 \
  -F model=whisper-1 \
  -F response_format=srt \
  -o subtitle.srt

1
00:00:00,000 --> 00:00:03,800
Ace Data Cloud Platform is testing the speech recognition endpoint.

2
00:00:03,800 --> 00:00:06,280
The quick brown fox jumps over the lazy dog.

curl -X POST 'https://api.acedata.cloud/v1/audio/transcriptions' \
  -H 'authorization: Bearer {token}' \
  -F file=@audio.mp3 \
  -F model=whisper-1 \
  -F response_format=verbose_json \
  -F 'timestamp_granularities[]=word'

{
  "task": "transcribe",
  "language": "english",
  "duration": 6.29,
  "text": "Ace Data Cloud Platform is testing the speech recognition endpoint. The quick brown fox jumps over the lazy dog.",
  "words": [
    {
      "word": "Ace",
      "start": 0.0,
      "end": 0.32
    },
    {
      "word": "Data",
      "start": 0.32,
      "end": 0.54
    },
    {
      "word": "Cloud",
      "start": 0.54,
      "end": 0.86
    }
  ]
}

curl -N -X POST 'https://api.acedata.cloud/v1/audio/transcriptions' \
  -H 'authorization: Bearer {token}' \
  -F file=@audio.mp3 \
  -F model=gpt-transcribe \
  -F stream=true

data: {"type":"transcript.text.delta","delta":"Hello"}

data: {"type":"transcript.text.done","text":"Hello world","usage":{"type":"tokens","input_tokens":14,"output_tokens":3,"total_tokens":17}}

from openai import OpenAI

client = OpenAI(base_url="https://api.acedata.cloud/v1", api_key="{token}")
with open("audio.mp3", "rb") as f:
    result = client.audio.transcriptions.create(model="whisper-1", file=f)
print(result.text)