POST /v1/audio/translations to get English text back. The endpoint reads the audio only from a multipart file field and has no URL option, so only the TypeScript SDK can call it directly; every other language posts the form with its standard HTTP client.
import { readFile } from "node:fs/promises";
const form = new FormData();
form.append("model", "openai/whisper-1");
form.append("file", new Blob([await readFile("interview.mp3")], { type: "audio/mpeg" }), "interview.mp3");
const translated = await client.generateTranslation(form as unknown as Record<string, unknown>);
console.log(translated.text);
# generate_translation() can't upload audio yet, so post the form with HTTPX.
import os
import httpx
with open("interview.mp3", "rb") as audio:
response = httpx.post(
"https://api.phaseo.app/v1/audio/translations",
headers={"Authorization": f"Bearer {os.environ['PHASEO_API_KEY']}"},
data={"model": "openai/whisper-1"},
files={"file": ("interview.mp3", audio, "audio/mpeg")},
timeout=120,
)
response.raise_for_status()
print(response.json()["text"])
// CreateTranslation() sends JSON, so post the form with net/http and mime/multipart.
var body bytes.Buffer
form := multipart.NewWriter(&body)
_ = form.WriteField("model", "openai/whisper-1")
part, _ := form.CreateFormFile("file", "interview.mp3")
audio, _ := os.ReadFile("interview.mp3")
_, _ = part.Write(audio)
_ = form.Close()
req, _ := http.NewRequest("POST", "https://api.phaseo.app/v1/audio/translations", &body)
req.Header.Set("Authorization", "Bearer "+os.Getenv("PHASEO_API_KEY"))
req.Header.Set("Content-Type", form.FormDataContentType())
resp, err := http.DefaultClient.Do(req)
// CreateTranslation() 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/whisper-1"), "model" },
{ new ByteArrayContent(await File.ReadAllBytesAsync("interview.mp3")), "file", "interview.mp3" },
};
var response = await http.PostAsync("https://api.phaseo.app/v1/audio/translations", form);
Console.WriteLine(await response.Content.ReadAsStringAsync());
<?php
// generateTranslation() 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/translations', [
'headers' => ['Authorization' => 'Bearer ' . getenv('PHASEO_API_KEY')],
'multipart' => [
['name' => 'model', 'contents' => 'openai/whisper-1'],
['name' => 'file', 'contents' => fopen('interview.mp3', 'r'), 'filename' => 'interview.mp3'],
],
]);
echo $response->getBody();
# generate_translation sends JSON, so post the form with Net::HTTP.
require 'net/http'
uri = URI('https://api.phaseo.app/v1/audio/translations')
request = Net::HTTP::Post.new(uri)
request['Authorization'] = "Bearer #{ENV.fetch('PHASEO_API_KEY')}"
request.set_form(
[['model', 'openai/whisper-1'], ['file', File.open('interview.mp3')]],
'multipart/form-data'
)
response = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |http| http.request(request) }
puts response.body
// The SDK's JSON helpers don't encode multipart, so post the form with java.net.http.
import java.io.IOException;
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpRequest.BodyPublishers;
import java.net.http.HttpResponse.BodyHandlers;
import java.nio.file.Path;
import java.time.Duration;
import java.util.UUID;
String baseUrl = System.getenv().getOrDefault("PHASEO_BASE_URL", "https://api.phaseo.app/v1")
.replaceAll("/+$", "");
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/whisper-1\r\n"),
BodyPublishers.ofString("--" + boundary + "\r\nContent-Disposition: form-data; name=\"file\"; filename=\"interview.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n"),
BodyPublishers.ofFile(Path.of("interview.mp3")),
BodyPublishers.ofString("\r\n--" + boundary + "--\r\n")
);
var request = HttpRequest.newBuilder(URI.create(baseUrl + "/audio/translations"))
.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());
| Language | SDK method | Can it upload a file? |
|---|---|---|
| TypeScript | client.generateTranslation(form) | Yes. Pass a FormData body and the SDK sends it as multipart unchanged; the cast is needed because the method’s type describes a JSON body. |
| Python | client.generate_translation(request) | No. It sends JSON, so post the form with HTTPX, as above. |
| Go | client.CreateTranslation(ctx, req) | No. It sends JSON, and the gateway rejects it with file is required. |
| C# | client.CreateTranslation(request) | No. It sends JSON, and the gateway rejects it with file is required. |
| PHP | $client->generateTranslation($request) | No. It sends JSON, and the gateway rejects it with file is required. |
| Ruby | client.generate_translation(...) | No. It sends JSON, and the gateway rejects it with file is required. |
| Java | None | No. Use java.net.http.HttpClient with a multipart body. |
post() helper sends JSON only.
Parameters
Field names are the form fields in every language.| Field | Notes |
|---|---|
model | Required. A translation model ID. |
file | Required. Up to 25 MB, as flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav or webm. |
prompt | Context to guide the translation. |
temperature | 0 to 1. |
response_format | json, text, srt, verbose_json or vtt. |
Response
AudioTranslationResponse:
{
"text": "Hello world"
}