Audio 语音处理

Authorization: Bearer sk-your-api-key

{
  "text": "这是一段测试语音的转写内容。"
}

curl -X POST "{BASE_URL}/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-your-api-key" \
  -F "file=@/path/to/audio.mp3" \
  -F "model=whisper-1" \
  -F "language=zh"

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="{BASE_URL}/v1"
)

with open("audio.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        language="zh"
    )

print(transcript.text)

curl -X POST "{BASE_URL}/v1/audio/translations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -F "file=@/path/to/audio.mp3" \
  -F "model=whisper-1"

curl -X POST "{BASE_URL}/v1/audio/speech" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "tts-1",
    "input": "你好，这是语音合成测试。",
    "voice": "nova",
    "response_format": "mp3",
    "speed": 1.0
  }' \
  --output speech.mp3

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="{BASE_URL}/v1"
)

response = client.audio.speech.create(
    model="tts-1",
    voice="nova",
    input="你好，这是语音合成测试。",
    speed=1.0
)

with open("speech.mp3", "wb") as f:
    f.write(response.content)

import OpenAI from 'openai';
import fs from 'fs';

const openai = new OpenAI({
  apiKey: 'sk-your-api-key',
  baseURL: '{BASE_URL}/v1',
});

async function main() {
  const mp3 = await openai.audio.speech.create({
    model: 'tts-1',
    voice: 'nova',
    input: '你好，这是语音合成测试。',
  });

  const buffer = Buffer.from(await mp3.arrayBuffer());
  fs.writeFileSync('speech.mp3', buffer);
}

main();