Connect Gemini to Your AI Agent

Give Gemini a prompt for writing or visual generation, and choose a model suited to your result.

8 tools API key

Try a Gemini Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill Gemini

Draft Text from a Brief

Generate a draft using your source material and tone requirements.

/oo Gemini: Use Gemini model [model ID] to write [document type] from these notes [notes], using [tone] and no more than [length].

Generate and Retrieve a Video

Start a Veo generation and wait for the finished video file.

/oo Gemini: Generate a Veo video using model [model ID] with this scene: [scene description]. Use [aspect ratio] and [duration]. Wait for completion and give me the video link.

Start Working with Gemini

  1. Install OOMOL

    Set up oo CLI and the oo Skill in your agent.

    Install OOMOL →
  2. Connect Gemini

    Connect a Gemini API key from Google AI Studio.

    Connect Gemini →
  3. Give Your Agent a Task

    Use /oo with the pages to read, the changes to make, and where to save the result.

    Connection Guide →

Choose Your Agent

  • A Gemini API key with access to the model you choose.
  • Image and finished-video delivery require the product’s file transit service. Video submission starts an operation; retrieve its result after processing.

Gemini Tools

This connection provides Gemini text and speech generation, embeddings, token counting, image generation, and asynchronous Veo video generation.

Text and Embeddings

Generate text or speech, embed supplied text, and count input tokens.

Images and Video

Generate images, submit Veo video jobs, and retrieve their status or finished files.

8 tools

List Models

List the available Gemini and Veo models.

gemini.list_models

Generate Content

Generate text or speech audio with Gemini models.

gemini.generate_content

Embed Content

Generate Gemini embeddings for text content.

gemini.embed_content

Count Tokens

Count the Gemini token usage for input text.

gemini.count_tokens

Generate Image

Generate an image with Gemini and return a transit URL.

gemini.generate_image

Generate Videos

Start a Gemini Veo video generation operation.

gemini.generate_videos

Get Videos Operation

Fetch the current status for a Gemini Veo operation.

gemini.get_videos_operation

Wait For Video

Poll a Gemini Veo operation and return the finished video via transit URL.

gemini.wait_for_video

Frequently Asked Questions

How do I choose a model?

Ask to list available models, then choose one that supports text, speech, images, embeddings, or video as needed. Model availability depends on your key.

Does submitting a video return the finished file?

Submission gives an operation name. Use it to check progress or wait for the finished video; processing may fail or filter the requested content.

What does speech generation produce?

With a speech-capable model and voice choice, generation can return encoded audio and its media type. Text generation returns the model’s text.

Connect Gemini

About Gemini ↗