Type your descriptive sentence into the Explainer Video Generator, choose your aspect ratio and duration, and wait 30 to 50 minutes for the tool to render an MP4 with narration, music, and subtitles.
What do I need to prepare before generating a video?
To make yours, you only need one descriptive sentence. The tool uses this single sentence to script, narrate, and assemble an explainer video with music and subtitles. Before you type your sentence, you must decide on the format, the length, and the language of the narration.
First, consider the aspect ratio. You can choose a landscape format at 16:9 or a vertical format at 9:16. The landscape format works for standard monitors, presentations, and wide-screen players. The vertical format fits mobile phone screens.
Next, choose the duration of your film. If you select the landscape 16:9 format, your video can run anywhere from 15 to 60 seconds. If you select the vertical 9:16 format, the tool restricts the duration to exactly 15 or 30 seconds.
Finally, choose the narration language. The generator supports narration in English and Chinese. Your input sentence should match the language you want the final narration to use. If you need examples of how to write a brief, you can read our Opus 5.5 Video Prompts.
When preparing your sentence, remember that the narration speed remains constant. In English, a narrator speaks at a specific pace, and in Chinese, the character density dictates the speed. If you choose a 15-second duration, the script generated from your sentence will be very brief. If you choose a 60-second duration, the system will expand on your descriptive sentence to fill the minute. A vertical 9:16 film running 30 seconds requires a sentence that provides enough context for a half-minute script. A landscape 16:9 film running 45 seconds needs a sentence with enough detail to prevent the narration from repeating itself. Take time to draft a sentence that clearly states the subject, the action, and the outcome.
How much does it cost to generate an explainer film?
The tool charges you in platform credits. The base rate is 100 credits for every started 10 seconds of video. To buy credits, you pay through FloatPass. The exchange rate is USD 1 for 250 platform credits.
Because the cost depends on every started 10-second block, a 15-second video costs the same as a 20-second video. Both cross into the second 10-second block. Here is a breakdown of the costs for the available durations:
| Duration | 10-Second Blocks Started | Credit Cost | Cost in USD |
|---|---|---|---|
| 15 seconds | 2 | 200 credits | $0.80 |
| 30 seconds | 3 | 300 credits | $1.20 |
| 45 seconds | 5 | 500 credits | $2.00 |
| 60 seconds | 6 | 600 credits | $2.40 |
To manage your payments, you will use FloatPass. FloatPass handles the transaction that converts your USD into platform credits. Since USD 1 equals 250 platform credits, you can calculate the exact dollar cost of any project. For example, if you want to generate five 60-second videos, each video costs 600 credits. Five videos require 3000 credits. At the conversion rate of 250 credits per dollar, 3000 credits cost exactly USD 12. If you generate ten 15-second vertical videos, each costs 200 credits, totaling 2000 credits. This batch would cost USD 8.
The system only deducts these credits when the video successfully finishes. Because a film that fails gives its credits back, you do not lose your balance if the generation process encounters an error. You can review the full pricing details to plan your budget.
How does the video generation process work?
Once you have your sentence and know your format, you enter the text into the Claude Video Generator for Explainer Videos. You select the duration and the aspect ratio, then submit the request.
A film takes about 30 to 50 minutes to make. During this time, the system writes the script based on your sentence, generates the voiceover in English or Chinese, selects the music, and creates the visuals. You do not need to stay on the page while the system processes the video.
The 30 to 50 minutes required to make a film involves several distinct rendering phases. First, the system analyzes your single descriptive sentence to understand the topic. Second, it drafts a script that fits the duration you selected, whether that is 15, 30, 45, or 60 seconds. Third, it generates the audio track. The narration is recorded in either English or Chinese, depending on your selection. Fourth, the system selects background music that fits the length of the audio track. Fifth, it renders the visual elements in either the 16:9 landscape or 9:16 vertical aspect ratio.
Finally, it compiles the visual track, the narration, and the music into a single MP4 file. It also generates the SRT file for the subtitles and extracts a frame for the cover image. When the 30 to 50 minutes have passed, the system provides these three files for each film. You can close your browser during this time and check back later to download your completed assets.
What are common mistakes to avoid when writing the sentence?
Many people try to pack too many distinct ideas into their single sentence. Because the maximum duration for a landscape video is 60 seconds, and the maximum for a vertical video is 30 seconds, the narration can only cover a limited amount of information. A long, complex sentence with multiple clauses will result in a rushed script or dropped information. Keep the sentence focused on one core concept.
Another common mistake involves the narration language. The tool only supports English and Chinese narration. If you write your sentence in a different language, the system cannot generate the corresponding voiceover. Always write your prompt in English or Chinese.
People also misunderstand how the duration affects the output. If you request a 15-second vertical video, the system only has time for a brief introduction and a quick conclusion. If you need to explain a complex topic, you should select the 60-second landscape option. You can read our Guides to explainer videos with Claude Opus 5.5 for more instructions on matching your sentence to the video duration.
Another mistake is choosing the wrong aspect ratio for your intended platform. If you plan to show the video on a mobile phone application, you should select the vertical 9:16 format. However, remember that vertical films run only 15 or 30 seconds. If your topic requires 60 seconds of explanation, you cannot use the vertical format. You must use the landscape 16:9 format, which runs 15 to 60 seconds. Attempting to force a 60-second script into a 30-second vertical video will result in a failed prompt or an incomplete message. Always verify that your chosen duration matches your aspect ratio.
How do I use the files provided after generation?
The tool gives you an MP4, an SRT file, and a cover image. The MP4 is the standard video format. You can upload this file directly to your website, send it in an email, or play it on a local machine.
The SRT file holds the text and timing for the subtitles. The MP4 does not have the text permanently burned into the visual track. Instead, you load the SRT file alongside the MP4 in your video player. This allows viewers to turn the subtitles on or off. If you upload the MP4 to a platform that supports closed captions, you will upload the SRT file in the designated subtitle field.
If you want to test the SRT file before you publish your video, you can do so on your own computer. Place the MP4 and the SRT file in the same folder. Give both files the exact same name. When you open the MP4 in a desktop video player, the player will automatically detect the SRT file and display the subtitles over the video. This allows you to verify the English or Chinese text against the narration.
The cover image serves as the thumbnail for your video. When you embed the MP4 on a webpage, the player usually displays a blank screen or a random frame before the user clicks play. You can set the cover image as the default visual so viewers see a clear picture before the video starts. These files give you the necessary parts to publish an Animated Data Story Video Maker project or an AI Product Launch Video Maker campaign.
Where else do people look for video generation tools?
When searching for ways to turn text into video, people often look at several different platforms. You might see people mention canva.com or adobe.com for general media creation. For AI video generation, people also look at heygen.com, pexo.ai, leadde.ai, and pictory.ai. We focus exclusively on turning one sentence into a narrated video with subtitles and music through the Opus 5.5 Video Generator: one sentence to a narrated film. You can browse our Blog for more information on how our specific features work.
Frequently asked questions
How long does it take to make an explainer video?
A film takes about 30 to 50 minutes to make.
What files do I get when the video is finished?
Each film comes with an MP4, subtitles in an SRT file, and a cover image.
What happens to my credits if the video fails to generate?
A film that fails gives its credits back to your account.
What languages can the narrator speak?
The narration is available in English or Chinese.
How long can vertical and landscape videos be?
Landscape 16:9 films run 15 to 60 seconds. Vertical 9:16 films run strictly 15 or 30 seconds.
How much does a video cost in credits?
A film costs 100 credits for every started 10 seconds. You pay through FloatPass, where USD 1 equals 250 platform credits.