---
title: "Translate ML"
slug: "dataflow-nodes-translate-ml"
updated: 2026-04-07T07:15:46Z
published: 2026-04-07T07:15:46Z
canonical: "docs.knovvu.com/dataflow-nodes-translate-ml"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://docs.knovvu.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Translate ML

A node that translates any input event with a `Text` attribute.

## Parameters

| name | description | default |
| --- | --- | --- |
| Source Language | Language of the source text. | tr-TR |
| Target Language | Language of the target text | en-US |
| Credential | API Key Credential for the OpenAI service | empty |
| OpenAI Model | OpenAI Model for the request | gpt-4.1-nano-2025-04-14 |
| Prompt | The specialized prompt with placeholders used for the translation. | You are a professional translation system specialized in ... |
| Model | Model information to be used by the service, required by some providers. |  |
| MaxTokens | Maximum amount of tokens to be used by the provider. | 2048 |
| Temperature | Temperature Value to be used by the provider | 0.0 |
| Provider | Name of the provider | VLLM |
| VLLM API Base | Enter VLLM Api Base, required if the provider is VLLM |  |
| Azure API Base | API Base string, required if the provider is Azure |  |
| Azure API Version | API Version string, required if the provider is Azure |  |
| API Key | API Key specific to the provider. Only required if the provider also requires it. |  |

## Inputs

### Audio

none

### Events

| name | description | known nodes that generate this event |
| --- | --- | --- |
| Any event that has `Data.Text` | Any Text based event. SR Milestone, etc. | SR Http, SR Websocket, Translate etc. |
| [Language Change](/v1/docs/events#language-change) | Language Change events that are tagged with either "Source" or "Target" will set their respective languages. | Language Identifier, Text Language Identifier, Event Tagger |

Language Change notes

The language change event from [Language Identifier](/v1/docs/dataflow-nodes-language-identifier) and [Text Language Identifier](/v1/docs/dataflow-nodes-text-language-identifier) should be tagged using the [Event Tagger Node](/v1/docs/dataflow-nodes-event-tagger) in order to effectively change this node's language .

## Outputs

### Audio

none

### Events

| name | description |
| --- | --- |
| [Translation](/v1/docs/events#translation) | Contains the translated text in `Data.Text` field. |

## Remarks

### Project Structure

The node expects events that have the `Text` field. Which means the node can be used with any and all SR nodes. A minimum viable project that utilizes Translate node can be built as such: ![image.png](https://cdn.document360.io/9bca2910-6a3b-4224-9470-43f91f9a6d57/Images/Documentation/image%28860%29.png)

With this project, one can use both Speech recognition and have the text translated to any desired language simultaneously.

Taking this a step further, we can construct a project such as: ![image.png](https://cdn.document360.io/9bca2910-6a3b-4224-9470-43f91f9a6d57/Images/Documentation/image%28861%29.png)

Which recognizes a speech, translates the text into another language, and uses TTS to create simultaneous audio outputs.

Keep This in Mind

Keep in mind that the [SR node](/v1/docs/dataflow-nodes-speech-recognition-sr-http) needs a model in `Source Language`, and [TTS node](/v1/docs/dataflow-nodes-tts-http) needs a Voice in the `Target Language` for this particular case.

Finally, here's a project that manipulates the `Translation` event so that it is `punctuated, filtered, normalized` before returning the output. ![image.png](https://cdn.document360.io/9bca2910-6a3b-4224-9470-43f91f9a6d57/Images/Documentation/image%28862%29.png)

Keep This in Mind

Also, keep in mind that the [SR node](/v1/docs/dataflow-nodes-speech-recognition-sr-http) needs to support the `Source Language`, and [Punctuation](/v1/docs/dataflow-nodes-punctuation), [Profanity Filter](/v1/docs/dataflow-nodes-profanity-filter), [Normalizer](/v1/docs/dataflow-nodes-normalizer) nodes need to support the `Target Language`.

### Detailed Workflow

Utilizes Http calls to SESTEK ML Realtime Translation with the provided node parameters. Raises a `Translation` event for every successful response.

### Supported flow types

Stream, Batch

## Release Notes

 
      

****v4.9.0****

      
          

- Added Node.