Skip to main content

Translation Quickstart

This guide makes your first translation against Shisa Translation. You will need an API key — create one in the Shisa platform. New accounts include $10 in free credits.

1. Get your API key​

Sign up for a Shisa AI account and obtain your API key from the Shisa platform. Include it in the Authorization header:

Authorization: Bearer YOUR_API_KEY
note

Translation authenticates with a standard bearer token — Authorization: Bearer YOUR_API_KEY. Shisa API keys start with shsk:; pass the full key. A missing or malformed token returns a 401 error. See Authentication for the full conventions.

tip

Keep your API key out of source control. Read it from an environment variable (for example SHISA_API_KEY) in real applications.

2. Make a request​

The request is multipart/form-data — send the text, source_lang, and target_lang as form fields. Set stream to "false" for a single JSON response.

curl
curl -X POST "https://api.shisa.ai/translate/" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "text=今日は素晴らしい天気ですね。" \
  -F "source_lang=ja" \
  -F "target_lang=en" \
  -F "stream=false"
Python
import requests

def translate_text(text, source_lang="ja", target_lang="en"):
    response = requests.post(
        "https://api.shisa.ai/translate/",
        headers={
            "Authorization": "Bearer YOUR_API_KEY"
        },
        data={
            "text": text,
            "source_lang": source_lang,
            "target_lang": target_lang,
            "stream": "false"
        }
    )
    return response.json()

# Example usage
result = translate_text("ビジネスの成功をお祈りします。")
print(result["choices"][0]["message"]["content"])
JavaScript
const translateText = async (text, sourceLang = 'ja', targetLang = 'en') => {
  const formData = new FormData();
  formData.append('text', text);
  formData.append('source_lang', sourceLang);
  formData.append('target_lang', targetLang);
  formData.append('stream', 'false');

  const response = await fetch('https://api.shisa.ai/translate/', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer YOUR_API_KEY',
    },
    body: formData,
  });

  const data = await response.json();
  return data.choices[0].message.content;
};

// Example usage
const translation = await translateText('日本とアメリカの架け橋になる');
console.log(translation); // Returns translated text

3. Read the response​

The API returns an OpenAI-style JSON response. The translated text is at choices[0].message.content:

{
  "id": "trans_20f537a6-da14-4c98-8ee3-063319c45072",
  "object": "translation.completion",
  "created": 1768299459,
  "model": "shisa-ai/chotto",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "お腹が空いた。"
      },
      "finish_reason": "stop"
    }
  ],
  "transcription": "I am hungry",
  "source_lang": "en",
  "target_lang": "ja",
  "balance": {
    "free": 1000,
    "premium": 0
  },
  "usage": {
    "prompt_tokens": 3,
    "completion_tokens": 1,
    "total_tokens": 4
  }
}

Set stream to "true" to receive the translation as Server-Sent Events instead — see the API reference for the full request and response schema, including the streaming format.

Next steps​