ActionVoyage AIUpdated September 2026

How do I embed text and images together with Voyage AI?

Short answer: You can multimodal embeddings in Voyage AI by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Voyage AI Multimodal Embeddings action to a workflow, map its 3 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

Multimodal Embeddings in Voyage AI — start free All 3 Voyage AI actions

Multimodal Embeddings in Voyage AI — start free

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Model model	options	Required	Model. Options: Voyage Multimodal 3
Text text	string	Optional	Text
Image URL image_url	string	Optional	A fully qualified URL (https://...) for the image url.

Sample request

{
  "model": "{{trigger.model}}",
  "text": "{{trigger.text}}",
  "image_url": "https://example.com/image.png"
}

Returns

{
  "data": [
    {
      "index": 0,
      "embedding": [
        0.012
      ]
    }
  ]
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Multimodal Embeddings.

Any of these apps can fire this action as part of a workflow.

Google Sheets → Voyage AI

2 Google Sheets triggers

HubSpot → Voyage AI

18 HubSpot triggers

FAQ

Questions about Multimodal Embeddings.

What does the Multimodal Embeddings action do in Voyage AI?

Embeds text and images in a shared vector space using Voyage's multimodal model. Use when you need cross-modal retrieval (find images by text query, or vice-versa).

What inputs does Multimodal Embeddings require?

Required: Model. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if Voyage AI returns an error?

The run history shows the failed step with its input and the error message Voyage AI returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.

Does Multimodal Embeddings support batch operations?

Run Multimodal Embeddings inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within Voyage AI's rate limits.

More actions

Other Voyage AI actions.

Action

Create Embeddings

Generates state-of-the-art text embeddings using Voyage AI, Anthropic's officially recommended embeddings provider. Strong default for RAG with Claude.

Action

Rerank

Reranks a list of candidate documents against a query, returning relevance scores. Standard last-mile step after vector retrieval to boost RAG precision before feeding context to the LLM.

Multimodal Embeddings in Voyage AI — start free