Count Tokens (Gemini)
Counts the number of tokens in text using Gemini tokenization. Useful for estimating costs, checking input limits, and optimizing prompts before making API calls.
ActionTry it
Integrate Gemini
with your AI CRM
Comprehensive Gemini integration supporting Gemini Omni video generation, Gemini Flash text generation (Nano Banana), chat completions, and multimodal AI capabilities via the Google Gemini API.
Explore Triggers and Actions
Embed Content (Gemini)
Generates text embeddings using Gemini embedding models. Converts text into numerical vectors for semantic search, similarity comparison, clustering, and classification tasks.
ActionTry it
Generate Content (Gemini)
Generates text content or speech audio from prompts using Gemini models. Supports text generation models (Gemini Flash, Pro) and text-to-speech models with configurable parameters. Generated text is nested at results[i].response.data.text. Output may be wrapped in markdown fences (e.g., ```html...```) or preceded by explanatory prose; strip these before file writing or rendering.
ActionTry it
Generate Image (Nano Banana)
Generates a downloadable image from a text prompt, defaulting to Nano Banana 2 Lite on managed connections and Gemini 3 Pro Image Preview on other connections. Managed requests require a 1–1000 character prompt and default 1K square settings; a timeout can leave the provider outcome unknown.
ActionTry it
Generate Videos
Starts an MP4 video generation from a text prompt with Gemini Omni 1.2 Flash (360p to 4k, 3 to 15 seconds, 16:9 or 9:16) and returns an operation_name right away. Generation usually takes one to a few minutes: pass operation_name to GEMINI_WAIT_FOR_VIDEO to get the file. On Instant the charge applies once Google accepts the job, so poll the same handle instead of resubmitting. Instant requests need a 1-1000 character prompt, an explicit duration and a price within the $2 per-request cap.
ActionTry it
Get Video Generation Status
Checks a Gemini Omni Flash video generation started by GEMINI_GENERATE_VIDEOS once, without waiting. Returns status pending, succeeded (with video_file) or failed. Reuse the same operation_name to poll; a new generation is a separate paid request.
ActionTry it
List Models (Gemini API)
Lists available Gemini models with their capabilities and limits. Useful for discovering supported models and their features before making generation requests.
ActionTry it
Wait and Download Video
Waits up to about 45 seconds for a Gemini Omni Flash video started by GEMINI_GENERATE_VIDEOS and returns the MP4 when ready. If it is still generating, returns pending=true with the same operation_name: call this action again with it, and do not resubmit a paid generation. success=true includes video_file; success=false means the generation failed.
ActionTry it
How the Gemini integration works
The Gemini integration connects your Dench AI CRM directly to Gemini, so agents can read and act on your Gemini data as part of everyday work — answering questions in chat, keeping your CRM in sync, and running automations without anyone copying data between tools.
8 actions are available for agents to invoke on your behalf. Every call runs through Gemini's own authorization, scoped to the account you connect.
Set up Gemini in Dench
- 1
Sign in to your Dench workspace and open Integrations.
- 2
Find Gemini and click Connect — you'll authorize access through Gemini's own sign-in flow. No API keys or code required.
- 3
Ask an agent to use Gemini in chat, or call it from an automation.
- 4
Manage or disconnect the connection any time from workspace settings.
Frequently asked questions
How does the Gemini integration work with Dench?
The Dench Gemini integration connects your AI CRM to Gemini, so AI agents can work with your Gemini data as part of chats, automations, and CRM workflows. You connect your account once, and every agent in your workspace can use it — governed by your workspace permissions.
What actions can AI agents perform with Gemini via Dench?
The Gemini integration currently exposes 8 actions, including Count Tokens (Gemini), Embed Content (Gemini), Generate Content (Gemini), Generate Image (Nano Banana), Generate Videos, and Get Video Generation Status. Agents invoke them on your behalf from chat or from automations.
Do I need to write code to connect Gemini to Dench?
No. You connect Gemini from your Dench workspace using Gemini's own sign-in and authorization flow — no API keys to copy, no glue code to maintain.
Is the Gemini integration secure?
Connections are authorized through Gemini's own authentication flow, and Dench stores only the authorization needed to act on your behalf. You can review and disconnect the Gemini connection from your workspace settings at any time.