n8n Workflow: Convert Image to Text with GROQ LLaVA V1.5

Turn any image into text—instantly—with GROQ LLaVA V1.5 inside n8n

This n8n automation workflow lets you send an image in Telegram and receive an AI-generated description (image-to-text) using the GROQ LLaVA V1.5 7B multimodal model—optimized for fast inference and visual understanding.

What this workflow does

• Telegram Trigger: The workflow listens for incoming messages in Telegram.
• Image Extraction: When an image is sent, it extracts the image data from the file.
• Vision Inference via GROQ LLaVA V1.5: The workflow calls the GROQ LLAVA V1.5 7B API to interpret the visual content and generate a description.
• Result Delivery: The generated text description is returned so users can read what the model “sees.”

Setup (Telegram bot)

• Open Telegram and search for @BotFather.
• Start a chat and type /newbot to create a new bot.
• Follow the prompts to choose a name and receive a unique API token.
• Save your access token and username, then use the workflow to begin sending images for descriptions.

Use cases

• Extract useful text-style descriptions from screenshots, diagrams, or UI images.
• Generate captions or summaries for images shared by team members in Telegram.
• Quick visual documentation for SaaS ops—send an image, get structured understanding in return.

Technical details

• Nodes/Tech stack: set, telegram, sticky note, http request, extract from file, telegram trigger.
• AI model: GROQ LLaVA V1.5 7B multimodal vision model for image understanding.
• Output: image-to-text descriptions generated from the provided image.