Your 6-Minute Guide to Auto-transcriptions on Bannerbear

Learn how to use Bannerbear's Transcribe feature to automatically transcribe videos and sync subtitles with a template designed to match your branding!
by Julianne Youngberg ·


    With video being such a popular form of online content, creators and brands need to introduce them in a way accessible to viewers. This means catering to a variety of devices and situations. A key way to do this? Subtitles.

    Bannerbear’s Transcribe feature makes it easy to automatically generate hundreds of transcribed videos with a single API call. You can also use nocode workflow builders in combination with our API to stitch clips together, include multiple audio tracks, and add brand elements. This article will give you a quick overview of subtitles and how you can automatically add them with Transcribe.

    The Importance of Adding Subtitles to Your Videos

    US adults are projected to watch social video for almost an hour each day by 2026, as video consumption rises. But with millions of hours of video content uploaded online daily, your audience isn’t short of viewing material.

    Subtitles are a simple way to increase video content quality and appeal to watchers. Their benefits include:

    • Improving viewers’ comprehension and retention
    • Boosting the probability of viewers completing the video
    • Increasing accessibility to hearing impaired-viewers

    Subtitles make video clips much more watchable and appealing to viewers. And while you can manually produce a transcript and sync the .srt file with your video, it can be a massive time drain. Bannerbear offers you a solution to generating video clips and transcribing them automatically.

    Sure, there are speech-to-text solutions out there for you to choose from. But with Bannerbear, you don’t just transcribe audio—you have subtitles synced to your videos, designed to match your branding, and automatically rendered for use.

    How to Use Bannerbear to Generate Auto-transcribed Videos

    Bannerbear is a flexible video generation tool with features to design templates, merge clips, add transitions, and more. You can generate subtitled videos by setting up a template with the Transcribe build pack. Then, it’s just a matter of connecting it to a trigger using the REST API or nocode tools like Zapier, Make, and Airtable.

    Prepare a Template

    Automatic transcription video templates are the same as regular templates—they just have video placeholders and are set up with the Transcribe build pack. Here’s a step-by-step setup guide:

    Step 1. Create a Regular Template

    Log into your Bannerbear account (get started for free! 🎉), then create and name a project. Click Create a Template.

    Screenshot of Bannerbear template page with red arrow pointing to create a template

    After specifying dimensions, you can open the editor and start designing your template. Add anything you’d like—text, brand assets, and even photos.

    You’ll need to have a dynamic text layer for your subtitles. Add one by clicking the + symbol next to New Layer and selecting Text under Dynamic Objects. Customize it however you’d like.

    Screenshot of Bannerbear editor with red arrow pointing to dynamic text

    Name the layer something that’s easy to locate later on, such as “subtitles” or “text”.

    Step 2. Toggle the Video Placeholder Option

    Look for the Video Placeholder option on the left sidebar and toggle it.

    Screenshot of Bannerbear editor with red arrow pointing to video placeholder

    Your video input will fill the visible green area. Click Save Template when you’re happy with your design.

    Step 3. Convert to Template to Video Template

    Your template design is ready, but it has to be converted into a video template. To do this, return to your project page and click Create a Video Template.

    Screenshot of Bannerbear template page with red arrow pointing to create a video template

    Select the corresponding template and choose Transcribe as the Build Pack.

    Screenshot of Bannerbear new video template setup

    Save the video template. You’ll now be on a setup page where you can specify the following:

    • Max length in seconds. This setting indicates the longest that all the videos you generate with this template can be.
    • Transcription engine. Bannerbear currently supports OpenAI Whisper and Google Transcribe engines.
    • Video frame word limit. This setting affects how Bannerbear splits up the text into different frames. You can adjust this as needed—lower word limits may leave less to read per frame, but frames might shift too quickly. (Note: This setting is only available for the Google Transcribe engine.)
    • Transcription layer. This setting is where you’ll choose the dynamic text layer you want subtitles to fill.
    • Transcription language. Bannerbear currently supports 10+ transcription languages including Chinese, French, Italian, and Spanish.
    • Approval setting. This setting allows you to decide whether or not you’d like to review subtitles before videos are rendered. (Note: See the section on how to manually approve subtitles below.)

    Screenshot of Bannerbear transcribe video template setup

    Click Save when done.

    Generate Your Auto-transcribed Video

    Your template is ready to use—now it’s just generating a video with auto transcriptions! There are several ways to do this, but we’ll cover instructions for the built-in API console and Zapier.

    Using the API Console - (⚡️ For testing purposes)

    Go to your video template page and scroll down to the API console section. You should see a standard POST request that looks something like this:

    Screenshot of Bannerbear video template API Console with post request outlined in red

    Insert your input media into the input_media_url section, keeping in mind that it must be a direct link.

    If you have any other modifiable fields whether text, colors, or photos, you can also specify changes under modifications.

    Screenshot of Bannerbear video template API Console with input media and modifications outlined in red

    Bear Tip 🐻: You can only use only one input media (with both video and audio) to generate a Video in Bannerbear. If you would like to merge multiple video clips and audio, such as in the case of a voiceover, you will have to generate a Movie beforehand.

    Click Send API Request when done.

    A response should now appear that shows details of your API request, such as time created, status, and render type.

    Screenshot of Bannerbear video template API Console with response outlined in red

    You will see output appear under the Videos section of the page as well. The status indicator will show whether a run is Complete , Failed , or—in the case that you’ve chosen manual approval before rendering— Pending Approval.

    Screenshot of Bannerbear video template output with red arrows pointing to status

    Click View Log Data to see full details of the API run.

    Using Zapier - (⚡️ For nocode workflows activated by a trigger)

    Log into Zapier and create a new zap. Add a trigger (eg. Schedule by Zapier, New Record in Airtable, etc.).

    Screenshot of Zapier Airtable new record trigger

    Add an action to Create Video in Bannerbear. You will need to connect your account using the key found by clicking the “Settings / API Key” button of the corresponding project of the Bannerbear app.

    Set up the action by selecting the corresponding video template and inserting input media URL, which can be a dynamic link from a previous step.

    Screenshot of Zapier Bannerbear create video action

    Add specifications for any modifiable fields, then test the action.

    You should see a new run appear under Videos in your Bannerbear app Logs.

    How to Manually Approve Subtitles Before Rendering

    You can modify video subtitles by setting up your build pack to require manual approval. When creating a Transcribe video template, make sure your Approval Setting is set to Manually approve before rendering.

    Screenshot of Bannerbear transcribe video template setup with approval setting outlined in red

    Whenever an API request is made to create a video with auto-transcriptions, you can then review it by visiting the template page.

    Scroll down to the Videos output section and click on entries marked Pending approval.

    Screenshot of Bannerbear video template output with red arrow pointing to pending approval status

    This will lead you to a preview page where you can make necessary changes before approving the video.

    Screenshot of Bannerbear manual transcript approval page

    Approving the video will allow it to proceed with rendering while rejecting it will terminate the run.

    A successful run will yield a video with subtitles according to your approval:

    Now the task can be added to a larger automation workflow, leaving you free to do more of the work that actually requires a human touch.


    Subtitles enhance the effectiveness of your video content. And with auto-transcriptions, you don’t have to produce them manually. Bannerbear makes it possible for you to design templates and produce beautifully designed videos with subtitles—all in one API call!

    About the authorJulianne Youngberg@paradoxicaljul
    Julianne is a technical content specialist fascinated with digital tools and how they can optimize our lives. She enjoys bridging product-user gaps using the power of words.

    Integrating Bannerbear Into Your Web Applications

    Bannerbear is an API that helps you automatically generate custom images, videos, and more from templates. In this article, we’ll explore how you can integrate Bannerbear into your web applications.

    5-Minute Crash Course to Facebook Single Image Ads (A 2024 Guide)

    Facebook single image ads can help both B2B and B2C brands reach and engage a diverse audience. Read our guide to learn what you need to know about this ad type.

    FFmpeg Video Editing Essentials: Trimming, Merging, Subtitling, and More!

    As an open-source tool, FFmpeg provides a wide array of functions for handling media files. Let's learn how to use FFmpeg to edit videos programmatically, including trimming, merging, adding subtitles, etc.

    Automate & Scale
    Your Marketing

    Bannerbear helps you auto-generate social media visuals, banners and more with our API and nocode integrations

    Your 6-Minute Guide to Auto-transcriptions on Bannerbear
    Your 6-Minute Guide to Auto-transcriptions on Bannerbear