Gemini CLI · Google's terminal agent for Gemini

Image and voice generation, native to Gemini CLI.

Gemini CLI's Skills spec went GA in early 2026 · same single-file markdown convention Anthropic and Codeium adopted. Gathos installs as a Gemini CLI skill so the agent can generate images and voiceover from any terminal session.

Install
curl -sL https://gathos.com/install.sh | bash

A sample session

You
gemini "Generate a Bauhaus-style poster for our launch event. Bold yellow background, the date 'May 18 2026' rendered in clean typography, our logo in the bottom-left."
Gemini CLI
Loading skill: /skills/event-poster (matched on intent).
Gemini CLI
→ POST /api/v1/image-generation, width=1024 height=1280...
Gemini CLI
✓ poster-launch-may18.png saved (1024×1280, 412 KB).
You
gemini "Now narrate the event description in Hindi using my saved voice clone."
Gemini CLI
→ /skills/ai-voiceover-loom with language=hi, voice=clone-1...
Gemini CLI
✓ event-narration-hi.mp3 saved (47 seconds).

Why pair Gathos with Gemini CLI

01
Gemini CLI skills, one install
Gathos installs into `~/.gemini/skills/`. Gemini CLI auto-discovers them on the next invocation. Project-scoped skills work too if you commit `.gemini/skills/` to your repo.
02
Pair Gemini reasoning with Gathos generation
Gemini CLI is exceptional at planning and tool-calling but does not include image generation in the standard distribution. Gathos fills that gap with one curl line.
03
Indic + global language coverage
Gathos TTS covers 600+ languages, including 12 first-class Indic languages. If your team is in India or your audience is multilingual, Gathos is one of very few options that ship Hindi, Tamil, Telugu, Marathi, Bengali, Gujarati, and Punjabi at native quality.
04
Flat pricing for terminal-driven workflows
Terminal agents are loop-friendly. Per-image and per-character APIs become bills before you notice. Gathos is $18/month flat with a 6-hour soft cap to prevent runaways.

Frequently asked questions

Is Gemini CLI Skills support stable?+
Yes, the skills spec went GA in early 2026 and is documented at the Gemini CLI docs site. Gathos targets the stable spec.
Can I use Gathos and the Gemini Imagen API in the same project?+
Yes. Many teams use Gemini Imagen for one-off hero shots (per-image pricing is fine at low volume) and Gathos for everything else. The Gemini CLI agent can route between them based on a tag in the prompt.
Does Gathos work with Gemini CLI in non-interactive (one-shot) mode?+
Yes. The skills export deterministic output paths so a CI script can call `gemini -p "do X"` and pick up the file by path.
How do I scope a skill to one project?+
Move the skill file from `~/.gemini/skills/` to `<project>/.gemini/skills/`. Project skills override global ones.
Are the skills MIT-licensed?+
Yes. The skill markdown files are MIT. Gathos itself (the API) is proprietary.

Using a different agent?

GitHub Copilot

Image and voice generation, plugged into GitHub Copilot.

GitHub Copilot supports custom agents and MCP servers in 2026, which means Gathos can be wired in as a callable tool inside any IDE that ships Copilot. The setup is one curl line and one config entry.

ChatGPT Custom GPTs

Image and voice generation, callable from a custom ChatGPT GPT.

Custom ChatGPT GPTs support Actions, which are HTTPS-callable tools the GPT can invoke during a conversation. Gathos exposes a clean OpenAPI schema so wiring it as an Action takes about ten minutes.

Continue

Image and voice generation in Continue.dev sessions.

Continue is the open-source alternative to Cursor, focused on developer control and self-hosting. It supports custom slash commands and tools through a clean config. Gathos plugs in as a callable tool so the agent can generate assets from the same editor session.

Aider

Image and voice generation, called from inside Aider sessions.

Aider is a terminal-first pair programmer that has stayed lean and fast. It does not ship with image generation or TTS, and the popular pattern is to bolt those on as external commands. Gathos slots in as a Bash-callable tool so an Aider session can generate assets without leaving the terminal.

Claude Code

Image generation and voice cloning for Claude Code.

Claude Code is the fastest-growing agent for power users. Gathos is the unified image + TTS API that plugs into Claude Code with a single install command. This page shows the install, a sample session, and the pre-built skills most teams install first.

Cursor

Image generation and voice cloning in Cursor.

Cursor is where millions of developers write code every day. Gathos plugs into Cursor as a set of agent-callable skills · you describe what you want in a chat message, Cursor runs the API, and the output lands in your project folder. Flat $18/month.

Windsurf

Image generation and voice cloning, native to Windsurf.

Windsurf shipped Cascade Skills in Wave 13 (January 2026), and the spec is the same single-file markdown convention Anthropic and Cursor adopted. Gathos plugs in as a Cascade Skill so the agent can generate thumbnails, product shots, voiceover, and dubbed videos without you leaving the editor.

Plug Gathos into Gemini CLI in one command.