Google Gemini
Generate text, images, video and speech with Google Gemini.
Connect it
In Keystile Automations → Connections → New connection, choose Google Gemini and sign in. Your AI tools and workflows then use it through Keystile; they never see the password or key.How connecting works.
Try it from your AI tool
Using Keystile, in Google Gemini: chat with gemini (Chat with Gemini, optionally remembering earlier messages).What it can do (11 actions)
| Action | What it does | Changes data |
|---|---|---|
| Chat with Gemini | Chat with Gemini, optionally remembering earlier messages. | |
| Count Tokens | Counts how many tokens a prompt will consume for a given Gemini model. | |
| Create Video | Generate a video from a text prompt using Google Veo models. | |
| Custom API Call | Make a custom API call to a specific endpoint | Yes |
| Generate Content | Send a prompt to Gemini and get a text response. | Yes |
| Generate Content from Image | Ask Gemini about an image and get a text response. | |
| Generate Content with File Search | Upload a file and have Gemini answer a prompt from it. | Yes |
| Generate Embeddings | Turns text into a list of numbers for search and similarity. | |
| Generate Image | Generate an image from a text prompt using a Gemini image model. | |
| List Models | Lists the models this API key can use, with limits where known. | |
| Text to Speech | Turn text into a spoken WAV audio file. |
How Keystile protects it
Every Google Gemini action is checked before it runs, whether it comes from an AI tool or a workflow. 3 of its actions change data; your rules, limits and budgets decide whether each is allowed, held for a person or stopped, and it all goes into the signed record.
Use Google Gemini with your AI assistant — safelyClaude, Cursor or ChatGPT do the work; Keystile checks every action first.
Get early access