Gemini logo
ConnectorGemini

Gemini integration for Claude and Codex

Create a Gemini connection, then control which Spaces can use its approved tools and data without pasting credentials into prompts or threads.

Use Gemini from Claude

Add the Gemini connection to a Space that runs Claude, then use it from every channel in that Space.

Use Gemini from Codex

Add the Gemini connection to a Space that runs Codex, then use it from every channel in that Space.

Use Gemini from Sidekick

Connect your own OpenClaw to Sidekick while type.com provides the conversations, permissions, connections, skills, and automations.

Developer Tools & IT

What the Gemini connector can do

Gemini is Google's multimodal AI model family, covering text, image, video, and embedding generation through one API. With a Gemini connection in type.com, a creative or product Space can ask Claude to generate an image, kick off a Veo video, or create embeddings for search, while Claude itself continues handling the conversation and reasoning.

One connection, many Spaces

Connect Gemini once, then decide which Spaces can use it in threads, skills, automations, and coding work.

What teams do with Gemini in type.com

Generate a concept image for review

Produce a quick image from a text description so the team has a visual to react to before committing to final creative.

Try asking
Generate an image with Gemini of a minimalist orange and white product box on a shelf.

Kick off a short video draft

Start a Veo video generation job from a prompt and check back once it finishes rendering.

Try asking
Generate a short Veo video with Gemini of a drone shot flying over a city skyline.

Build embeddings for semantic search

Convert a batch of text into embeddings to support similarity search or clustering in another part of the workflow.

Try asking
Embed these 30 support article titles with Gemini so we can cluster similar topics.

Representative actions

  • Count Tokens (Gemini)

    Counts how many tokens a piece of text uses under Gemini's tokenizer, useful for cost and limit checks.

  • Embed Content (Gemini)

    Converts text into numerical embeddings for semantic search, similarity, or clustering tasks.

  • Generate Content (Gemini)

    Generates text or speech audio from a prompt using Gemini's text and text-to-speech models.

  • Generate Image (Nano Banana)

    Creates an image from a text prompt using Gemini's image-generation models.

  • Generate Videos (Veo)

    Starts a video generation job from a text prompt using Google's Veo models, returning an operation to track progress.

Connection

API and auth details

Gemini API lets developers build with Google multimodal models for text, image, audio, video, code, structured output, function calling, grounding, embeddings, and agentic workflows. Integrations can use Google AI Studio keys, Gemini Developer API, Firebase AI Logic, or Vertex AI depending on deployment and governance needs.

FAQ

Questions people ask before connecting Gemini

Can Claude generate images and video with Gemini in type.com?

Yes. Once a Gemini connection is shared with a Space, the agent can generate images, video, or embeddings as part of a thread conversation.

How does type.com authenticate with Gemini?

This Gemini connection does not require a separate sign-in step; an admin sets it up once and shares it with the right Spaces.

Can Gemini generation be scheduled in type.com?

Yes. A recurring creative task, such as generating a weekly social image, can be set up as a type.com automation.

Is this the same as a Gemini MCP server?

Not exactly. type.com uses connectors and connections to give selected Spaces access to approved app tools and data. Some connectors use hosted MCP, while others use OAuth, API keys, service accounts, or custom APIs.

More developer tools & it connectors

All Developer Tools & IT integrations