STT 语音转文本

NUWA 提供统一的语音转文本（STT）接口，兼容 OpenAI 规范，支持实时流式转写与文件转写，适用于通话记录、会议纪要、客服质检等场景。

接口规格

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",  # NUWA 控制台生成的 Key
    base_url="https://api.nuwaapi.com/v1"
)

with open("/path/to/audio.wav", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
    )

print(transcript.text)

TypeScript

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1",
});

async function main() {
  const transcript = await client.audio.transcriptions.create({
    model: "whisper-1",
    file: fs.createReadStream("/path/to/audio.wav"),
  });

  console.log(transcript.text);
}

main().catch(console.error);

• 返回格式：JSON，包含转写文本和可选的分段信息

---

请求参数（文件转写）

参数	类型	是否必填	说明
file	file	是	音频文件，常见格式：mp3、mp4、mpeg、mpga、m4a、wav、webm
model	string	是	模型 ID，默认 whisper-1
language	string	否	提示音频语言，例如 zh、en，可提升准确度
temperature	number	否	采样温度，控制随机性，默认 0
prompt	string	否	先验文本/词汇提示，帮助消除歧义
response_format	string	否	输出格式，默认 json，支持 text、srt、verbose_json 等

---

调用示例

基础转写

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1"
)

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

print(transcript.text)

TypeScript

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1",
});

async function main() {
  const transcript = await client.audio.transcriptions.create({
    model: "whisper-1",
    file: fs.createReadStream("/path/to/audio.mp3"),
  });

  console.log(transcript.text);
}

main().catch(console.error);

指定语言与提示词

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1"
)

with open("/path/to/meeting.wav", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        language="zh",
        prompt="本次会议讨论了 API 集成和结算问题",
    )

print(transcript.text)

TypeScript

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1",
});

async function main() {
  const transcript = await client.audio.transcriptions.create({
    model: "whisper-1",
    file: fs.createReadStream("/path/to/meeting.wav"),
    language: "zh",
    prompt: "本次会议讨论了 API 集成和结算问题",
  });

  console.log(transcript.text);
}

main().catch(console.error);

获取字幕格式（SRT）

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://api.nuwaapi.com/v1"
)

with open("/path/to/video_audio.m4a", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        response_format="srt",
    )

print(transcript)  # 返回 SRT 字幕字符串

TypeScript

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1",
});

async function main() {
  const transcript = await client.audio.transcriptions.create({
    model: "whisper-1",
    file: fs.createReadStream("/path/to/video_audio.m4a"),
    response_format: "srt",
  });

  console.log(transcript); // 返回 SRT 字幕字符串
}

main().catch(console.error);

---

返回示例（简化）

{
  "text": "欢迎使用 NUWA 语音转文本接口。"
}

---