A node that translates any input event with a Text attribute. Uses OpenAI with a specialized prompt for translation.
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-3.5-turbo |
| Prompt | The specialized prompt with placeholders used for the translation. | You are a professional translation system specialized in ... |
| Role | The role of the speaker you want replaced in the {{role}} placeholder for the prompt | |
| OpenAI Address | OpenAI Address, you can also prefer your Azure OpenAI address | https://api.openai.com/v1/chat/completions |
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 | Language Change events that are tagged with either "Source" or "Target" will set their respective languages. | Language Identifier, Text Language Identifier, Event Tagger |
The language change event from Language Identifier and Text Language Identifier should be tagged using the Event Tagger Node in order to effectively change this node's language .
Outputs
Audio
none
Events
name |
description |
|---|---|
| Translation | Contains the translated text in Data.Text field. |
Remarks
Requirements
The node needs an OpenAI Api key to perform. To learn more about getting an API Key and finding it, you can refer to the OpenAI API page .
After getting your API Key, you can learn about finding and securely using your key following the instructions on this page .
You can also see which models are available through the OpenAI Models page.
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:
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:
Which recognizes a speech, translates the text into another language, and uses TTS to create simultaneous audio outputs.
Finally, here's a project that manipulates the Translation event so that it is punctuated, filtered, normalized before returning the output.
Also, keep in mind that the SR node needs to support the Source Language, and Punctuation, Profanity Filter, Normalizer nodes need to support the Target Language.
Detailed Workflow
Utilizes Http calls to OpenAI Api with the provided API Key Credential. Raises a Translation event for every response.
Supported flow types
Stream, Batch