Golpo AI Complete Tutorial: Every Feature, Control, and Setting Explained

Feature deep dive: Picture in Picture

Using Own Narration with a webcam or uploaded presenter video? The dedicated guide covers round overlays, split-screen layouts, positioning, framing, plan availability, and seven finished examples. Open the Picture-in-Picture guide →

Golpo AI turns text prompts, documents, audio recordings, and screen captures into animated explainer videos — the kind with hand-drawn whiteboard illustrations and professional narration that you see on YouTube education channels and in corporate training programs. You describe what you want, and Golpo writes the script, generates the visuals, adds narration and music, and delivers a finished video in ten to fifteen minutes.

This tutorial walks through every part of the platform. Every button, toggle, dropdown, and input field on the video creation page is covered, along with which pricing plan unlocks each feature. By the end you will know exactly what every control does and how to use it.

Watch the full video tutorial here:

Last verified July 26, 2026 against the live Golpo AI product, current pricing page and official API documentation. Product controls, limits, and plan availability can change; current in-app and checkout values govern. This is a product-owned guide.

What Golpo AI Does

Golpo is an AI video generator focused on explainer and whiteboard-style videos. You give it a topic — either by typing a prompt, uploading a document, recording your voice, or providing an existing audio or video file — and it produces a narrated, animated video.

The output is not a slideshow or a template you fill in. Golpo generates original hand-drawn illustrations, syncs them to narration, and animates them with a pen-drawing effect. The result looks like what a professional whiteboard animation studio would produce, but it takes minutes instead of weeks.

Common use cases include:

• YouTube educational content and explainers
• Corporate training and employee onboarding videos
• Product demos and marketing videos
• Sales enablement and personalized prospect videos
• Course content for educators and coaches
• Social media content in vertical or horizontal formats

Getting Started: Login

Golpo supports Google or Microsoft login. Please go to https://video.golpoai.com and click on "Getting Started" on the top or "Start for Free" as shown in this screenshot.

The Create Video Page

When you log in to Golpo and click Create New Video, you land on the video creation page. This is where everything happens. The page is organized from top to bottom: input area at the top, video style selection in the middle, and detailed settings at the bottom.

Let us go through every element on this page.

The Top Bar

Across the top of the page you will see:

• Credits — your remaining video credits, shown as a number (for example, 117.562). If you are on a team plan, it says "team credits" next to it. One credit equals roughly one minute of generated video
• Plan — your current plan name (Free, Starter, Creator, Growth, Business, or Scale), displayed as a clickable link
• Voice Clone — a button that takes you to the voice cloning feature (Business and Scale plans)
• Library — opens your video library where all generated videos are stored
• Upgrade — takes you to the pricing page
• Profile icon — click to see your name, email, and a dropdown menu with Add-ons, Edit Video, Team, Manage Billing, and Sign Out

On the left side of the top bar, there is an Instructions dropdown. This lets you save and load reusable instruction presets — handy if you frequently create videos with the same tone, style, or specific guidelines.

Prompt Content: The Main Input Area

The large text box labeled Prompt Content is where you describe your video. This is the primary way to tell Golpo what to make.

You can type anything from a single sentence to a detailed multi-paragraph description. The placeholder text reads: "Describe your video/podcast topic, perspective, and instructions in any language..."

Good prompts include:

• The topic you want explained
• The perspective or audience (for example, "explain this to a five-year-old" or "this is for senior software engineers")
• Specific points you want covered
• The tone (professional, casual, humorous, academic)

Avoid

• Don't put special characters or emojis.

You can write your prompt in any language, and Golpo will generate the video in that language (for creator and above plans). Language option is available from the creator plan and above. For Free and Starter plans, whatever language you provide the prompt in, it'll generate the video in English.

The Attach Button

Below the prompt text box, there is an Attach button. Click it to upload documents — PDFs, Word files, or other text documents. Golpo reads the document, extracts the content, and uses it as the basis for your video. This is powerful for turning existing company documents, research papers, product manuals, or lesson plans into videos without rewriting anything.

You can combine a document attachment with a text prompt. For example, attach your product brochure and add a prompt like "Create a two-minute overview of this product focused on the pricing and key features, targeting small business owners."

Available on: All plans

The Two Toggles: Own Narration and Script Mode

In the top-right corner of the input area, there are two toggles that fundamentally change how Golpo creates your video.

Own Narration

When Own Narration is OFF (the default), Golpo generates the narration for you using AI voices. You provide the topic, and Golpo writes the script and speaks it. A detailed tutorial is available here: https://video.golpoai.com/guide/golpo-ai-own-narration-guide

When Own Narration is ON, the prompt text box disappears and is replaced with audio and video input options:

Upload Audio or Video — drag and drop or click to select a common audio or video format. For video uploads, choose Audio in Video to use only the audio track or Picture in Picture to keep the presenter visible beside the generated content.

The uploaded video picture is removed only when Audio in Video is selected. Picture in Picture preserves the presenter video and displays it in the chosen overlay or split-screen layout.

• Record Audio — record narration directly from your microphone.
• Record Webcam — capture camera and audio, then choose Audio in Video or Picture in Picture for the final result.

Golpo uses the supplied audio as the narration instead of generating an AI voice, transcribes the recording, and creates visuals that match it. The recording determines the duration and spoken language, so the normal duration, AI voice, and Voice Instructions controls do not apply in Own Narration mode.

For an uploaded or webcam-recorded video, open the Picture-in-Picture guide to compare round-overlay and split-screen layouts. Before generation, certify that you own the recording or have explicit permission to use it.

Use this when you want to use your own voice, a branded AI voice from ElevenLabs or similar services, an existing recording like a Zoom call or podcast, or when you want precise word-for-word control over the narration.

Available on: Business, Scale, and Enterprise subscription plans. It is also included in the current Pay As You Go feature set. Confirm current availability on the live pricing page.

Script Mode

When Script Mode is ON, the text you supply becomes the narration. Instead of describing a topic and letting Golpo research and draft the script, paste only the words that should be spoken; put visual direction in Video Instructions.

This is essential when:

• Compliance or legal requires specific approved language
• You have already written a script and want it read exactly
• You need total control over what is said without AI interpretation

Access: Script Validation is included with Growth and higher plans, available as a Creator add-on, and unavailable on Starter. Edit script before creating video is the separate checkbox that activates the pre-render review step. See the Prompt Mode vs Script Mode guide.

Video Style: Golpo Canvas vs. Golpo Sketch

Below the input area, you choose between two video generation engines:

• Golpo Canvas — Produces scene-based animations in 11 named visual styles. Ten established style families offer Compact and Expanded profiles. Compact combines more components within each scene so viewers can see more of the explanation together and retain the relationships between its ideas. Expanded distributes those components across more scenes, giving each component more visual space and revealing the explanation in smaller steps. The earlier profiles are now named Expanded. The new Notebook style is Compact-only. Open the all Canvas styles guide or watch every Compact/Expanded pair plus Notebook.

Custom Style: Business plans and above can create a reusable Canvas style from an image, a video, or a written description. See the Custom Style guide.