Speech Recognition & Translation

curl https://www.qingbo.dev/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

from openai import OpenAI

client = OpenAI(
    base_url="https://www.qingbo.dev/v1",
    api_key="YOUR_API_KEY"
)

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

print(transcript.text)

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

const client = new OpenAI({
  baseURL: 'https://www.qingbo.dev/v1',
  apiKey: 'YOUR_API_KEY'
});

const transcript = await client.audio.transcriptions.create({
  model: 'whisper-1',
  file: fs.createReadStream('audio.mp3')
});

console.log(transcript.text);

package main

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

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

    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.qingbo.dev/v1/audio/transcriptions", body)
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", writer.FormDataContentType())

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    result, _ := io.ReadAll(resp.Body)
    fmt.Println(string(result))
}

import java.net.http.*;
import java.net.URI;
import java.nio.file.*;

public class Main {
    public static void main(String[] args) throws Exception {
        String boundary = "----FormBoundary" + System.currentTimeMillis();
        byte[] fileBytes = Files.readAllBytes(Path.of("audio.mp3"));

        String body = "--" + boundary + "\r\n"
            + "Content-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\n"
            + "Content-Type: audio/mpeg\r\n\r\n";
        String fieldPart = "\r\n--" + boundary + "\r\n"
            + "Content-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n"
            + "--" + boundary + "--\r\n";

        byte[] requestBody = new byte[body.getBytes().length + fileBytes.length + fieldPart.getBytes().length];
        System.arraycopy(body.getBytes(), 0, requestBody, 0, body.getBytes().length);
        System.arraycopy(fileBytes, 0, requestBody, body.getBytes().length, fileBytes.length);
        System.arraycopy(fieldPart.getBytes(), 0, requestBody, body.getBytes().length + fileBytes.length, fieldPart.getBytes().length);

        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://www.qingbo.dev/v1/audio/transcriptions"))
            .header("Authorization", "Bearer YOUR_API_KEY")
            .header("Content-Type", "multipart/form-data; boundary=" + boundary)
            .POST(HttpRequest.BodyPublishers.ofByteArray(requestBody))
            .build();

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

{
  "text": "欢迎使用 清波 API 语音识别服务。"
}