音频转写（Audio Transcriptions）

音频接口的具体能力取决于已配置的模型和渠道。本页介绍 OpenAI 音频转写接口；同一分类下还提供文本转语音和音频翻译。上传文件时使用 multipart/form-data。

语音转文字

POST /v1/audio/transcriptions
Authorization: Bearer sk-your-api-key
Content-Type: multipart/form-data

调用示例

cURL

curl -X POST "https://www.walmind.cn/v1/audio/transcriptions" \
  -H "Authorization: Bearer $API_KEY" \
  -F "file=@audio.mp3" \
  -F "model=whisper-1"

JavaScript

import fs from 'node:fs';

const form = new FormData();
form.append('file', new Blob([fs.readFileSync('audio.mp3')]), 'audio.mp3');
form.append('model', 'whisper-1');

const response = await fetch('https://www.walmind.cn/v1/audio/transcriptions', {
  method: 'POST',
  headers: {Authorization: `Bearer ${process.env.API_KEY}`},
  body: form,
});

console.log(await response.json());

Python

import os
import requests

with open("audio.mp3", "rb") as audio_file:
    response = requests.post(
        "https://www.walmind.cn/v1/audio/transcriptions",
        headers={"Authorization": f"Bearer {os.environ['API_KEY']}"},
        files={"file": ("audio.mp3", audio_file, "audio/mpeg")},
        data={"model": "whisper-1"},
    )
response.raise_for_status()
print(response.json())

Go

package main

import (
    "bytes"
    "fmt"
    "io"
    "mime/multipart"
    "net/http"
    "os"
)

func main() {
    file, _ := os.Open("audio.mp3")
    defer file.Close()

    var body bytes.Buffer
    writer := multipart.NewWriter(&body)
    part, _ := writer.CreateFormFile("file", "audio.mp3")
    io.Copy(part, file)
    writer.WriteField("model", "whisper-1")
    writer.Close()

    req, _ := http.NewRequest("POST", "https://www.walmind.cn/v1/audio/transcriptions", &body)
    req.Header.Set("Authorization", "Bearer "+os.Getenv("API_KEY"))
    req.Header.Set("Content-Type", writer.FormDataContentType())

    resp, err := http.DefaultClient.Do(req)
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()
    result, _ := io.ReadAll(resp.Body)
    fmt.Println(string(result))
}

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.nio.file.Files;
import java.nio.file.Path;
import java.io.ByteArrayOutputStream;
import java.nio.charset.StandardCharsets;

public class TranscribeAudio {
    public static void main(String[] args) throws Exception {
        String boundary = "----WalmindBoundary";
        byte[] audio = Files.readAllBytes(Path.of("audio.mp3"));
        ByteArrayOutputStream body = new ByteArrayOutputStream();
        body.write(("--" + boundary + "\r\n").getBytes(StandardCharsets.UTF_8));
        body.write("Content-Disposition: form-data; name=\"model\"\r\n\r\n".getBytes(StandardCharsets.UTF_8));
        body.write("whisper-1\r\n".getBytes(StandardCharsets.UTF_8));
        body.write(("--" + boundary + "\r\n").getBytes(StandardCharsets.UTF_8));
        body.write("Content-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\n".getBytes(StandardCharsets.UTF_8));
        body.write("Content-Type: audio/mpeg\r\n\r\n".getBytes(StandardCharsets.UTF_8));
        body.write(audio);
        body.write(("\r\n--" + boundary + "--\r\n").getBytes(StandardCharsets.UTF_8));

        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://www.walmind.cn/v1/audio/transcriptions"))
            .header("Authorization", "Bearer " + System.getenv("API_KEY"))
            .header("Content-Type", "multipart/form-data; boundary=" + boundary)
            .POST(HttpRequest.BodyPublishers.ofByteArray(body.toByteArray()))
            .build();

        HttpResponse<String> response = HttpClient.newHttpClient()
            .send(request, HttpResponse.BodyHandlers.ofString());
        System.out.println(response.body());
    }
}

响应示例：

{"text": "识别出的文字内容"}