Windsurf · Cascade-powered AI editor by Codeium

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.

Install
curl -sL https://gathos.com/install.sh | bash && echo "Reload Windsurf"

A sample session

You
I need 5 vertical reels from podcast-ep-12.mp3. Use my saved voice clone for the trailer narration. Style matches my channel template.
Windsurf
Running Cascade Skill /skills/podcast-clip-factory. Pulling 12 highlights from the transcript, picking the top 5...
Windsurf
→ 5 vertical MP4s (1080×1920) saved to ./output/. Cover images generated for each clip. Trailer.mp3 narrated in your voice.
You
Add burnt-in captions in your channel font.
Windsurf
Re-running with caption overlay enabled. ETA 90 seconds.

Why pair Gathos with Windsurf

01
Cascade Skills are markdown · the install is a curl line
Windsurf reads Cascade Skill files from `.windsurf/skills/`. Gathos installs into that directory. Commit the folder so every teammate inherits the same agent-callable tools without setup.
02
Two APIs, one editor, flat bill
Image generation and TTS share one API key in Gathos. Generate a thumbnail and the voiceover for the same video in a single Cascade session. No swap-tab, no two dashboards.
03
Asset files land in your repo
Windsurf invokes the Gathos API and writes the PNG or MP3 to a path you specified, ready to commit. No copy-paste from a web UI.
04
Bounded cost surface for AI-generated code
Cascade is enthusiastic about loops. A per-image API can hand you a $40 surprise. Gathos is flat $18/month with a 6-hour fair-use window · runaway scripts hit a soft wall, not a billing wall.

Skills most teams install first

Each is a single curl command. Install one, install all five.

Creator workflow

YouTube thumbnails

The job: you run a YouTube channel and you need a fresh thumbnail for every video. Stock-photo subscriptions and Midjourney cost money per image. Gathos gives you unlimited generation at a flat $18/month, plus it can actually render readable text inside the image.

Ecommerce workflow

Shopify product shots

Small Shopify stores spend $200 to $1,500 per SKU on photography. With Gathos you upload one reference shot, describe the scene, and get 20 clean variants: flatlay, on-model, lifestyle, seasonal. $18/month flat, no per-image cost.

Async video

AI voiceover for Loom

Loom videos are the backbone of remote teams. The one thing that kills them: you cannot re-record when you want to tweak the script, and you cannot ship them in Spanish or Hindi without a second take. Gathos clones your voice from a 30-second sample and speaks any script in 600+ languages.

Video localization

Auto-dub videos

You have a 10-minute video in English. You want Hindi, Spanish, and Portuguese versions without hiring three voice actors and a translator. Upload it to Gathos: the skill transcribes, translates, re-reads the translation in your cloned voice, and re-aligns to your on-screen timing.

Podcast growth

Podcast clip factory

Every podcast episode is a month of social content if you chop it right. The chopping is the hard part. Gathos bundles the whole pipeline: transcript, highlight picking, vertical reframe, caption burn-in, cover art generation, and a 60-second trailer narrated in your voice.

Frequently asked questions

Which Windsurf version do I need?+
Wave 13 or later (January 2026 onward) when Cascade Skills were stabilized. The install script checks your version and warns if you are below.
Do I commit the skills folder?+
Yes. Cascade reads `.windsurf/skills/` as part of the project. Committing the folder means everyone on the team gets the same tools without per-machine setup.
Can I run multiple Gathos skills in parallel?+
Yes. The Pro plan allows 10 concurrent jobs by default; admins can raise this. Cascade handles the parallelism if you ask for "20 reels in batches of 5".
What if I want a custom skill on top of Gathos?+
Copy any of the bundled skills as a template, edit the front-matter and the API call section, save into `.windsurf/skills/`. Cascade picks it up on next reload.
Does Gathos work in Cascade Mode chat or only in the agent?+
Both. The skills are invokable from chat-mode prompts and from agent runs. Same install path.

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.

Gemini CLI

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.

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.

Plug Gathos into Windsurf in one command.