STT（音声認識）

import { readFile } from "node:fs/promises";

const form = new FormData();
form.append("model", "openai/gpt-4o-transcribe");
form.append("language", "en");
form.append("file", new Blob([await readFile("call.mp3")], { type: "audio/mpeg" }), "call.mp3");

const transcript = await client.generateTranscription(form as unknown as Record<string, unknown>);
console.log(transcript.text);

# generate_transcription() can't send multipart yet, so post the form with HTTPX.
import os
import httpx

with open("call.mp3", "rb") as audio:
    response = httpx.post(
        "https://api.phaseo.app/v1/audio/transcriptions",
        headers={"Authorization": f"Bearer {os.environ['PHASEO_API_KEY']}"},
        data={"model": "openai/gpt-4o-transcribe", "language": "en"},
        files={"file": ("call.mp3", audio, "audio/mpeg")},
        timeout=120,
    )
response.raise_for_status()
print(response.json()["text"])

// CreateTranscription() sends JSON, so post the form with net/http and mime/multipart.
var body bytes.Buffer
form := multipart.NewWriter(&body)
_ = form.WriteField("model", "openai/gpt-4o-transcribe")
_ = form.WriteField("language", "en")
part, _ := form.CreateFormFile("file", "call.mp3")
audio, _ := os.ReadFile("call.mp3")
_, _ = part.Write(audio)
_ = form.Close()

req, _ := http.NewRequest("POST", "https://api.phaseo.app/v1/audio/transcriptions", &body)
req.Header.Set("Authorization", "Bearer "+os.Getenv("PHASEO_API_KEY"))
req.Header.Set("Content-Type", form.FormDataContentType())

resp, err := http.DefaultClient.Do(req)

// CreateTranscription() sends JSON, so post the form with HttpClient.
using var http = new HttpClient();
http.DefaultRequestHeaders.Authorization =
    new("Bearer", Environment.GetEnvironmentVariable("PHASEO_API_KEY"));

using var form = new MultipartFormDataContent
{
    { new StringContent("openai/gpt-4o-transcribe"), "model" },
    { new StringContent("en"), "language" },
    { new ByteArrayContent(await File.ReadAllBytesAsync("call.mp3")), "file", "call.mp3" },
};

var response = await http.PostAsync("https://api.phaseo.app/v1/audio/transcriptions", form);
Console.WriteLine(await response.Content.ReadAsStringAsync());

<?php
// generateTranscription() sends JSON, so post the form with Guzzle, which Composer installed with the SDK.
require 'vendor/autoload.php';

$http = new GuzzleHttp\Client();

$response = $http->post('https://api.phaseo.app/v1/audio/transcriptions', [
    'headers' => ['Authorization' => 'Bearer ' . getenv('PHASEO_API_KEY')],
    'multipart' => [
        ['name' => 'model', 'contents' => 'openai/gpt-4o-transcribe'],
        ['name' => 'language', 'contents' => 'en'],
        ['name' => 'file', 'contents' => fopen('call.mp3', 'r'), 'filename' => 'call.mp3'],
    ],
]);

echo $response->getBody();

# generate_transcription sends JSON, so post the form with Net::HTTP.
require 'net/http'

uri = URI('https://api.phaseo.app/v1/audio/transcriptions')
request = Net::HTTP::Post.new(uri)
request['Authorization'] = "Bearer #{ENV.fetch('PHASEO_API_KEY')}"
request.set_form(
  [['model', 'openai/gpt-4o-transcribe'], ['language', 'en'], ['file', File.open('call.mp3')]],
  'multipart/form-data'
)

response = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |http| http.request(request) }
puts response.body

// The SDK's JSON helpers don't encode multipart, so post the form with java.net.http.
import java.io.IOException;
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpRequest.BodyPublishers;
import java.net.http.HttpResponse.BodyHandlers;
import java.nio.file.Path;
import java.time.Duration;
import java.util.UUID;

String baseUrl = System.getenv().getOrDefault("PHASEO_BASE_URL", "https://api.phaseo.app/v1")
    .replaceAll("/+$", "");
String apiKey = System.getenv("PHASEO_API_KEY");
String boundary = "phaseo-" + UUID.randomUUID();
var body = BodyPublishers.concat(
    BodyPublishers.ofString("--" + boundary + "\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nopenai/gpt-4o-transcribe\r\n"),
    BodyPublishers.ofString("--" + boundary + "\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nen\r\n"),
    BodyPublishers.ofString("--" + boundary + "\r\nContent-Disposition: form-data; name=\"file\"; filename=\"call.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n"),
    BodyPublishers.ofFile(Path.of("call.mp3")),
    BodyPublishers.ofString("\r\n--" + boundary + "--\r\n")
);
var request = HttpRequest.newBuilder(URI.create(baseUrl + "/audio/transcriptions"))
    .header("Authorization", "Bearer " + apiKey)
    .header("Content-Type", "multipart/form-data; boundary=" + boundary)
    .timeout(Duration.ofSeconds(60))
    .POST(body)
    .build();
var response = HttpClient.newHttpClient().send(request, BodyHandlers.ofString());
if (response.statusCode() < 200 || response.statusCode() >= 300) {
    throw new IOException("HTTP " + response.statusCode() + ": " + response.body());
}
System.out.println(response.body());

result = client.generate_transcription({
    "model": "mistral/voxtral-mini-transcribe-2",
    "file_url": "https://example.com/call.mp3",
    "language": "en",
})

print(result["text"])

resp, err := client.CreateTranscription(context.Background(), map[string]interface{}{
  "model":    "mistral/voxtral-mini-transcribe-2",
  "file_url": "https://example.com/call.mp3",
  "language": "en",
})
if err != nil {
  panic(err)
}
fmt.Println(resp["text"])

var response = await client.CreateTranscription(new Dictionary<string, object>
{
    ["model"] = "mistral/voxtral-mini-transcribe-2",
    ["file_url"] = "https://example.com/call.mp3",
    ["language"] = "en",
});

$response = $client->generateTranscription([
    'model' => 'mistral/voxtral-mini-transcribe-2',
    'file_url' => 'https://example.com/call.mp3',
    'language' => 'en',
]);

echo $response['text'];

response = client.generate_transcription(
  model: 'mistral/voxtral-mini-transcribe-2',
  file_url: 'https://example.com/call.mp3',
  language: 'en'
)

let response = client.post("/audio/transcriptions", &json!({
    "model": "mistral/voxtral-mini-transcribe-2",
    "file_url": "https://example.com/call.mp3",
    "language": "en"
}))?;

println!("{}", response.body["text"]);