How to beginner · 3 min read

How to translate text with Claude API

Q: How to translate text with Claude API

Use the anthropic Python SDK to call client.messages.create with the claude-3-5-sonnet-20241022 model, passing a translation prompt in the messages parameter and the system parameter to set context. The API returns the translated text in response.content[0].text.

Quick answer

Use the anthropic Python SDK to call client.messages.create with the claude-3-5-sonnet-20241022 model, passing a translation prompt in the messages parameter and the system parameter to set context. The API returns the translated text in response.content[0].text.

PREREQUISITES

Python 3.8+
Anthropic API key
pip install anthropic>=0.20

Setup

Install the anthropic SDK and set your API key as an environment variable.

Install the SDK: pip install anthropic
Set your API key in your shell: export ANTHROPIC_API_KEY='your_api_key_here'

bash

pip install anthropic

output

Collecting anthropic
  Downloading anthropic-0.20.0-py3-none-any.whl (20 kB)
Installing collected packages: anthropic
Successfully installed anthropic-0.20.0

Step by step

This example shows how to translate English text to Spanish using the Claude API. The system parameter sets the assistant's role, and the messages array contains the user prompt.

python

import os
import anthropic

client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

response = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=500,
    system="You are a helpful assistant that translates English text to Spanish.",
    messages=[{"role": "user", "content": "Translate this to Spanish: 'Hello, how are you today?'"}]
)

translated_text = response.content[0].text
print("Translated text:", translated_text)

output

Translated text: Hola, ¿cómo estás hoy?

Common variations

You can translate to other languages by changing the system prompt or user message. For asynchronous calls, use asyncio with client.messages.acreate. To use a different Claude model, update the model parameter accordingly.

python

import asyncio
import os
import anthropic

async def translate_async(text: str, target_language: str):
    client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])
    system_prompt = f"You are a helpful assistant that translates English text to {target_language}."
    user_message = {"role": "user", "content": f"Translate this to {target_language}: '{text}'"}
    response = await client.messages.acreate(
        model="claude-3-5-sonnet-20241022",
        max_tokens=500,
        system=system_prompt,
        messages=[user_message]
    )
    return response.content[0].text

async def main():
    result = await translate_async("Good morning, have a nice day!", "French")
    print("Translated text:", result)

asyncio.run(main())

output

Translated text: Bonjour, passez une bonne journée !

Troubleshooting

If you get an authentication error, verify your ANTHROPIC_API_KEY environment variable is set correctly.
If the response is incomplete, increase max_tokens.
For unexpected output, ensure your system prompt clearly instructs the model to translate.

✅

Key Takeaways

Use the anthropic SDK with client.messages.create for Claude translation tasks.
Set the system parameter to specify translation instructions clearly.
Async calls are supported via client.messages.acreate for non-blocking translation.
Adjust max_tokens to control response length and avoid truncation.
Always keep your API key secure and set via environment variables.

Verified 2026-04 · claude-3-5-sonnet-20241022

Verify ↗