音频

音频接口通常包含两类能力：

• 文本转语音（TTS）
• 语音转文本（STT）

文本转语音

POST https://rtai.jnrongtu.com/v1/audio/speech

常见参数

• model
• input
• voice
• response_format
• speed

示例

curl -X POST "https://rtai.jnrongtu.com/v1/audio/speech"   -H "Content-Type: application/json"   -H "Authorization: Bearer sk-xxxx"   -d '{
    "model": "tts-1",
    "input": "你好，欢迎使用 Token中转站。",
    "voice": "alloy"
  }'   --output speech.mp3

语音转文本

POST https://rtai.jnrongtu.com/v1/audio/transcriptions

常见参数

• file
• model
• language
• response_format

Python 示例

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxx",
    base_url="https://rtai.jnrongtu.com/v1"
)

with open("audio.mp3", "rb") as f:
    resp = client.audio.transcriptions.create(
        model="whisper-1",
        file=f,
        language="zh",
    )
print(resp.text)