Translate Tool

Use the Translate tool to enable AI-powered workflows to translate content across supported languages. When you connect this tool to an AI node, the AI model can dynamically translate text from videos, documents, transcripts, and other content based on user requests and workflow context.

In this article, you learn how to add, configure, and test the Translate tool in your workflow.

Concept

The Translate tool is a tool node that provides AI models with the ability to translate content between languages. Unlike regular workflow nodes that execute in sequence, this tool is invoked by an AI node only when the model determines that translation is needed.

Key capabilities:

• Multi-language translation - Translate content between all supported languages
• Source language detection - Automatically detect the source language when not specified
• Content-aware translation - Preserve meaning, tone, and context during translation
• Metadata inclusion - Return translated content with source and target language information

Understand how the tool works

This section explains how the Translate tool operates within a workflow and how it connects to other nodes.

Tool connectors

In the Workflow Designer, nodes use colored connectors to indicate the type of connection and data flow. The Translate tool uses the green connector, which is specific to tool nodes.

Execution flow

When a workflow runs, the Translate tool operates in this sequence:

1. The AI node receives user input from the chatbot.
2. The AI model analyzes the input and determines whether translation is needed.
3. If translation is needed, the AI invokes the Translate tool through the green connector.
4. The tool processes the content with the specified target language and generates the translation.
5. The translated content and language metadata are stored in the field specified in Output Field.
6. The AI node accesses the translated content and composes a response for the user.

┌─────────────┐      ┌─────────────┐      ┌──────────────────┐
│ User Query  │ ───► │  AI Node    │ ───► │  Translate       │
└─────────────┘      └─────────────┘      │ (Green Connector)│
                            ▲              └──────────────────┘
                            │                       │
                            └── state.data.translation ◄┘

When to use this tool

Use the Translate tool when your workflow requires:

• AI-driven translation of content based on natural language requests
• On-demand translation of transcripts, captions, or document text
• Multi-language support for users who need content in their preferred language
• Translation of retrieved search results or summaries into a target language

Add the Translate tool to your workflow

Follow these steps to add the Translate tool to your workflow canvas.

1. Go to Portal Settings > Chatbot > Workflow.

2. Select an existing workflow or create a new workflow.

3. In the Node Library, expand the Tools category.

4. Drag Translate Tool onto the canvas.

Connect the tool to an AI node

After you add the Translate tool to the canvas, connect it to an AI node.

1. Locate your AI node (such as an LLM node) on the canvas.

2. Drag a connection line from the green connector to the input connector on the Translate tool node.

3. Release to create the connection. A green connector (●) indicates a successful tool connection.

NOTE: The green connector indicates that the tool is available to the AI node for on-demand invocation. The tool doesn't execute in sequence with other nodes, it executes only when the AI model decides to invoke it.

Configure the Translate tool

Select the Translate node to open the Node Configuration Panel. You can configure the following options:

Description

Instructions for the LLM on how and when to use this tool. The default description provides guidance including:

• When to invoke translation (user requests content in another language, asks for a translation)
• How to determine source and target languages from user input
• Supported language codes and naming conventions

The AI uses this description to determine when translation is appropriate. For example, when a user asks "Translate this document into Spanish," the AI reads the description to understand it should invoke the Translate tool with target_language set to Spanish.

TIP: Keep the default description unless you need to customize the AI's translation behavior for specific use cases.

Translation parameters

You can configure the following options:

• Input Field: The text content to translate. The AI typically populates this from retrieved content such as transcripts, document text, or descriptions. Use ${state.data.content_text} to reference content retrieved by other tools or nodes, or enter static text for testing.

• Target Language: The language to translate the content into. The AI determines this from the user's request. Enter a language name such as Spanish, French, or Arabic, or use a language code such as es, fr, or ar. Use ${state.data.target_lang} for dynamic values.

All translation parameters support Fixed (static value) and Expression (dynamic value using ${variable} syntax) input modes.

Chunking settings

These settings control how large content is split for translation.

• Chunk Size: The maximum number of characters in each chunk when translating large content. The tool splits content into chunks of this size to ensure reliable translation. Default is 4000.

Model settings

These optional settings let you override the default AI model used for translation.

• Model Provider: The AI provider to use for generating translations. When left empty, the tool uses the default model configured for the workflow. Specify a provider when you need a particular model for translation quality or language support.

• Model ID: The specific model identifier from the selected provider. When left empty, the tool uses the provider's default model.

• System Prompt: Instructions that guide how the AI performs translation. The default prompt includes a {target_language} placeholder that is automatically replaced with the specified target language at runtime. Customize this when you need translations in a specific tone, formality level, or domain terminology.

• Temperature: Controls the randomness of the translated output. Lower values produce more literal and consistent translations. Higher values produce more creative and natural-sounding translations. Default is 0.3.

• Max Token Limit: The maximum number of tokens the model can generate in the translation response. Use this to manage token consumption for large content.

Output settings

• Output Field: Variable name where the translated content is stored for use by other nodes. Click to select an existing variable or create a new one. The output includes the translated text and source/target language metadata. The AI node and subsequent workflow nodes access results using ${state.data.<variable_name>}. For example, if you name it translation, access it as ${state.data.translation}.

Test the configuration

After you configure the Translate tool, test the workflow to verify correct behavior.

1. Go to Portal Settings > Chatbot > Agents.

2. Select the agent associated with your workflow, or create a new agent and assign your workflow.

3. Open the chatbot interface in the portal.

4. Enter a query that should trigger translation. For example:

   • "Translate this video transcript into French"
   • "What does this document say in Spanish?"
   • "Give me the Arabic version of this content"

5. Verify that the agent returns accurately translated content.

6. Check that the response includes the correct target language and preserves the meaning of the original content.

7. If results don't match expectations, return to the Workflow Designer and adjust your configuration.

Supported languages

The Translate tool supports all languages available through the configured AI model. Common supported languages include but are not limited to:

Language	Code
English	en
Spanish	es
French	fr
German	de
Arabic	ar
Chinese (Simplified)	zh
Japanese	ja
Portuguese	pt
Russian	ru
Korean	ko
Hindi	hi
Italian	it
Dutch	nl
Turkish	tr

NOTE: Language support depends on the AI model configured in your workflow. Check your AI provider's documentation for the complete list of supported languages.

Best practices

• Pair the Translate tool with the Search Mashup tool or Read Content tool so that the AI can retrieve content and translate it in a single interaction.
• For large documents, consider pairing with the Summarize tool to generate a summary first and then translate the summary.
• Specify the source language when working with content that might be misidentified by automatic detection.
• Test translations with native speakers when accuracy is critical for your use case.

Related articles

• Tools in VIDIZMO Intelligence Hub
• Search Mashup tool
• Summarize tool
• Workflow Designer
• Variables
• Nodes

Did you find this article helpful?

Sorry we couldn't be helpful. Help us improve this article with your feedback.

Your email*

Your feedback*

Need more information

Difficult to understand

Inaccurate/irrelevant content

Missing/broken link

Glad we could be helpful. Thanks for the feedback.

Your response has been recorded. Thank you for the feedback.