OpenAI integration

What the OpenAI package does

Provides a simple interface to access the OpenAI API with simplified outputs (msg.text, msg.images, msg.audio). Supports GPT-5.4, GPT-5.2, GPT-5, o4-mini, o3, DALL-E 3, GPT-Image-2, Whisper, and more, plus an agent Toolkit for AI-driven image generation.

Comprehensive OpenAI API integration supporting text generation (GPT-5, GPT-4o, o3, o4-mini with vision, streaming, JSON mode, tool calling, and reasoning effort control), image generation and editing (GPT-Image-1 with transparent backgrounds, DALL-E 3/2), image variations (DALL-E 2), text-to-speech (GPT-4o Mini TTS, TTS-1 HD with 13 voices and voice instructions), audio transcription (GPT-4o Transcribe with speaker diarization, Whisper), audio translation to English, vector embeddings (single and batch, text-embedding-3 with configurable dimensions), cosine similarity search over CSV embedding files, content moderation (omni-moderation), and file storage management (upload, download, list, delete, metadata). Auth via OpenAI API key from vault or Robomotion AI Credits.

Namespace

Robomotion.OpenAI

Latest version

3.3.2 (64 versions published)

Written in

Go

Categories

Artificial Intelligence

OpenAI nodes (21)

These are the node IDs an agentic flow or an RPA bot uses, exactly as they appear in the Flow Designer and in flow code. An agent tool node can also be called by an AI agent on its own. The Toolkit node hands an agent several of the package operations at once.

Platforms

The OpenAI package runs on Windows, macOS and Linux robots. Any Robomotion robot on these operating systems can run a flow that uses it.

How to install the OpenAI package

1. Open Packages in the Robomotion Flow Designer.
2. Search for OpenAI or Robomotion.OpenAI, then click Install on its card.
3. The OpenAI nodes appear in the node palette for everyone in the workspace, because installation is per workspace.

From a terminal, the Robomotion CLI installs the same package:

robomotion install Robomotion.OpenAI

Templates that use OpenAI

One ready-made template uses OpenAI nodes in their flows. Open one to start from a working flow.

• RAG with DeepSeek

  Retrieval-augmented generation over your own documents, with the retrieval handed to the agent instead of done for it. Documents are read, chunked, embedded and stored in LanceDB - an embedded vector database that is just a directory on disk. A DeepSeek Agent then answers questions through a search_knowledge tool built from ordinary flow nodes, writing its own queries and searching as many times as a question needs, with the source document named against every fact.

Related integrations

Packages that share a category or keywords with OpenAI. It is filed under Artificial Intelligence.

• Chat AssistantCreate powerful AI chat assistants for automation - supports both guided workflow assistants that follow step-by-step processes and fully agentic conversational assistants
• ClaudeProvides a simple interface to access the Anthropic Claude API. Claude is Anthropic's powerful AI assistant capable of advanced reasoning, coding, analysis, and creative tasks.
• ElevenLabs AIIt connects to ElevenLabs AI. It is an natural-sounding speech synthesis and text-to-speech software, using artificial intelligence and deep learning
• Google Document AIProvides a simple interface to access Google Document AI, a service that extracts structured data from documents using machine learning and enables automated document processing.
• Google GeminiProvides a simple interface to access the Google Gemini API (Gemini 3.5 / 3.1, Nano Banana image models, and more), plus an agent Toolkit for AI-driven image generation.
• Leonardo AIConnects to Leonardo AI API, which allows you to integrate cutting-edge create image technology into your flows.

OpenAI documentation

The OpenAI package reference on docs.robomotion.io documents each node and its properties.