For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DASHBOARDPLAYGROUNDDOCSCOMMUNITYLOG IN
Guides and conceptsAPI ReferenceRelease NotesLLMUCookbooks
Guides and conceptsAPI ReferenceRelease NotesLLMUCookbooks
  • Get Started
    • Introduction
    • Installation
    • Creating a client
    • Playground
    • FAQs
  • Models
    • An Overview of Cohere's Models
    • Aya
    • Embed
    • Rerank
  • Text Generation
    • Introduction to Text Generation at Cohere
    • Using the Chat API
    • Reasoning
    • Image Inputs
    • Streaming Responses
    • Predictable Outputs
    • Advanced Generation Parameters
    • Tool Use
    • Tokens and Tokenizers
        • Multilingual interpreter
    • Summarizing Text
    • Safety Modes
  • Embeddings (Vectors, Search, Retrieval)
    • Introduction to Embeddings at Cohere
    • Semantic Search with Embeddings
    • Multimodal Embeddings
    • Batch Embedding Jobs
  • Going to Production
    • API Keys and Rate Limits
    • Going Live
    • Deprecations
    • How Does Cohere's Pricing Work?
  • Integrations
    • Integrating Embedding Models with Other Tools
    • Cohere and LangChain
    • LlamaIndex and Cohere
  • Deployment Options
    • Overview
    • SDK Compatibility
  • Tutorials
    • Cookbooks
    • LLM University
    • Build Things with Cohere!
    • Agentic RAG
    • Cohere on Azure
  • Responsible Use
    • Security
    • Usage Policy
    • Command A Technical Report
    • Command R and Command R+ Model Card
  • Cohere Labs
    • Cohere Labs Acceptable Use Policy
  • More Resources
    • Cohere Toolkit
    • Datasets
    • Improve Cohere Docs
LogoLogodocs
DASHBOARDPLAYGROUNDDOCSCOMMUNITYLOG IN
Text GenerationPrompt EngineeringPrompt Library

How to Build a Multilingual interpreter

Was this page helpful?
Edit this page
Previous

Summarizing Text with the Chat Endpoint

Next
Built with

Interpret between a wide variety of different languages.

Prompt

Interpret the text below into into French, Spanish, Italian, German, Brazilian Portuguese,
Japanese, Korean, Simplified Chinese, and Arabic:
The customer is having a problem with a printer that is not connecting to the computer. He
tried restarting both the computer and the printer.

Output

French: Le client rencontre un problème avec une imprimante qui ne se connecte pas à l'ordinateur.
Il a essayé de redémarrer l'ordinateur et l'imprimante.
Spanish: El cliente tiene un problema con una impresora que no se conecta a la computadora.
Ha intentado reiniciar ambas, la computadora y la impresora.
Italian: Il cliente ha un problema con la stampante che non si connette al computer. Ha provato
a riavviare sia il computer che la stampante.
German: Der Kunde hat ein Problem mit einem Drucker, der sich nicht mit dem Computer verbindet.
Er hat sowohl den Computer als auch den Drucker neu gestartet.
Brazilian Portuguese: O cliente está com problema em uma impressora que não está se conectando
ao computador. Ele tentou reiniciar tanto o computador quanto a impressora.
Japanese: お客様はプリンターがパソコンに繋がらない問題を抱えています。お客様はパソコンとプリンターの両方を再起動しました。
Korean: 고객이 컴퓨터에 연결되지 않는 프린터 문제로 고민하고 있습니다. 고객은 컴퓨터와 프린터를 모두 재부팅해 보았습니다.
Simplified Chinese: 客户的打印机无法连接到电脑,他尝试重启了电脑和打印机。
Arabic: يواجه العميل مشكلة
مع طابعة لا تتوصّل بالكمبيوتر، وقد حاول إعادة تشغيل الكمبيوتر والطابعة دون جدوى.

API Request

PYTHON
1import cohere
2
3co = cohere.ClientV2(api_key="<YOUR API KEY>")
4
5response = co.chat(
6 model="command-a-plus-05-2026",
7 messages=[
8 {
9 "role": "user",
10 "content": """
11 Interpret the text below into into French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic:
12 The customer is having a problem with a printer that is not connecting to the computer. He tried restarting both the computer and the printer.
13 """,
14 }
15 ],
16)
17
18print(response.message.content[0].text)