音频

提供 TTS（文本转语音） 与 STT（语音转文本） 能力。

语音合成 POST

POST https://api.nassaapi.xyz/audio/speech

请求参数

参数	类型	必填	说明
model	string	✅	tts-1 / tts-1-hd
input	string	✅	要合成的文本
voice	string	✅	alloy / echo / fable / onyx / nova / shimmer
response_format	string	❌	mp3（默认） / opus / aac / flac
speed	number	❌	语速倍率 0.25–4.0，默认 1.0

示例请求

cURL

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

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxx",
    base_url="https://api.nassaapi.xyz"
)

response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="你好，欢迎使用NassaApi 中转站。"
)
response.stream_to_file("speech.mp3")

JavaScript

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

const client = new OpenAI({
  apiKey: 'sk-xxxx',
  baseURL: 'https://api.nassaapi.xyz',
});

const response = await client.audio.speech.create({
  model: 'tts-1',
  voice: 'alloy',
  input: '你好，欢迎使用NassaApi 中转站。',
});

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

语音识别 POST

POST https://api.nassaapi.xyz/audio/transcriptions

请求参数

参数	类型	必填	说明
model	string	✅	whisper-1
file	file	✅	音频文件（mp3 / wav / m4a 等）
language	string	❌	ISO 639-1 语言代码，如 zh
response_format	string	❌	json（默认） / text / srt / vtt
temperature	number	❌	采样温度，0–1

示例请求

cURL

curl -X POST "https://api.nassaapi.xyz/audio/transcriptions" \
  -H "Authorization: Bearer sk-xxxx" \
  -F file="@audio.mp3" \
  -F model="whisper-1" \
  -F language="zh"

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxx",
    base_url="https://api.nassaapi.xyz"
)

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

响应

{
  "text": "你好，欢迎使用NassaApi 中转站。"
}