How to Create a Video With Multiple Languages in Golpo

You can create one video with multiple spoken languages by writing those languages directly into a Script Only script in Golpo. This guide shows three finished examples: English with German, French, and Hindi in a single 46.50-second video; an English–Spanish lesson; and an English–Bengali lesson. Each teaches “What’s your name?”, “How old are you?”, and “Where do you live?”

The useful detail: all three examples had Language set to English. The script itself supplies the language switches. Watch the videos below, then copy their exact scripts and saved settings.

We'll learn some English to German translations. "What's your name?" is translated as "Wie heißt du?" and "How old are you?" as "Wie alt bist du?" and "Where do you live?" is translated as "Wo wohnst du?"

Now we'll learn some English to French translations. "What's your name?" is translated as "Comment tu t'appelles ?" and "How old are you?" as "Quel âge as-tu ?" and "Where do you live?" is translated as "Où habites-tu ?"

And now we'll learn some English to Hindi translations. "What's your name?" is translated as "तुम्हारा नाम क्या है?" and "How old are you?" as "तुम्हारी उम्र कितनी है?" and "Where do you live?" is translated as "तुम कहाँ रहते हो?"

We'll learn some English to Spanish translations. "What's your name?"	is translated as "¿Cómo te llamas?" and "How old are you?" as	"¿Cuántos años tienes?" and "Where do you live?" is traslated as	"¿Dónde vives?"

We'll learn some English to Bengali translations. "What's your name?" is translated as "তোমার নাম কী?" and "How old are you?" as "তোমার বয়স কত?" and "Where do you live?" is translated as "তুমি কোথায় থাকো?"

The video settings used in all three examples

These are the saved settings behind the embedded videos, recorded on October 21, 2026. The settings downloads under each script preserve the relevant saved field names and values; use the readable labels below when recreating the examples in Golpo.

The duration selection is not the exported runtime. The two short examples were saved with a 15-second selection, but their files run for 18.93 and 20.43 seconds. The longer example was saved with a 1-minute selection and exports at 46.50 seconds.

No extra translation directions, reference documents, uploaded media, custom narrator instructions, or manual scene map were supplied. The language pairs and transitions are already in the Script. The visual style changes the presentation; it does not replace the mixed-language wording.

How to create your own video with multiple languages

1. Choose the phrases and write the translations first. Decide what the learner should hear. For a phrase lesson, write each source question followed immediately by its translation. Use a fluent reviewer to check meaning, spelling, and the level of formality before generation.
2. Open Golpo and choose Script Only mode. Paste the complete narration into the Script field. The script should contain the actual words in every language, rather than a request such as “make this bilingual.” See the Prompt Mode vs Script Mode guide for the input-mode controls.
3. Make the transitions part of the narration. Start with “We’ll learn some English to Spanish translations.” For another section, add a spoken transition such as “Now we’ll learn some English to French translations.” Put a blank line between language sections so you can review the structure easily.
4. Start with the demonstrated settings. To reproduce these examples, use Canvas, Female 1, English for Language, and English for Display Language. Choose a duration suitable for the complete script and check the character allowance shown in your current interface. Keep native characters, accents, and punctuation.
5. Choose how the video should look. Try Chalkboard Color, Editorial Compact, or Notebook Infographic. All three examples used Fast pacing, Auto visual animation, no background music, and Generate on-screen text using only the script content enabled. The Canvas styles guide helps you choose the layout.
6. Review the script and create the video. Read every source-and-translation pair aloud before submitting. If you use the separate Edit script before creating video control, approve that script before rendering. The examples above were generated directly with that review control off.
7. Watch and listen through every language switch. Check pronunciation, omitted words, pacing, visible characters, and the exported length. Ask someone fluent in each target language to review the result before teaching from it or sending it to customers.

How to write the script so the language switches are clear

Write a spoken relationship between the two phrases. “What’s your name?” followed by “is translated as” and the target-language question gives the narration a clear order. A list of language names or an instruction to translate does not supply the words you want spoken.

Use one language pair per short section. The first example repeats the same three English questions in German, French, and Hindi sections. That repetition lets the viewer compare translations without learning a new question at every switch. Add a spoken transition when the target language changes.

Keep the original writing system. The Hindi phrases use Devanagari, and the Bengali phrases use Bengali script. Preserve characters such as ß, ¿, ñ, and accented French letters. If you need transliteration for your audience, decide whether it belongs in the spoken lesson or in the visual directions before you add it.

Keep production directions in their own fields. Putting “switch to Hindi now” or “[show the translation]” into Script Only mode may turn those words into narration. Write a natural spoken transition in Script, and place visual directions in Video Instructions.

The three examples left Video Instructions and Voice Instructions empty. If your lesson needs extra direction, use the Video Instructions guide for drawings and labels, and the Voice Instructions guide for delivery. Those would be changes to the demonstrated configuration.

Spoken language and on-screen text need separate checks

The Script supplies the multilingual narration. Display Language is a separate setting for visible wording. In these examples it stayed on English, while the scripts supplied the German, French, Hindi, Spanish, and Bengali phrases visible in the finished videos.

Generate on-screen text using only the script content was enabled in all three. That setting limits the source wording available for generated labels; it does not make every word appear on screen, set the spoken language, or replace proofreading. See the on-screen text from script guide for a fuller explanation.

Check the final video against the supplied script. Generated display text can still need a correction: for example, the Bengali video shows “What’s your nme?” where the supplied English script says “What’s your name?” The original video is embedded here unchanged so you can judge the output yourself.

What to check if your multilingual video needs a correction

• A phrase is missing or changed: confirm that Script Only mode is enabled and that the exact phrase is present in Script. A topic prompt and a complete narration serve different purposes.
• A language switch sounds rushed: use shorter phrases and clearer sentence breaks, then review the new render. For a lesson with distinct language sections, the sentence-to-scene selection guide explains how to plan scene boundaries.
• The pronunciation needs work: have a fluent reviewer identify the exact phrase. Revise that phrase or test voice delivery on a short passage before creating a longer lesson. The same voice may not perform equally across every language or accent.
• The visible translation differs from the spoken one: compare both with the approved script and review the display-text setting. A correct script still needs a visual check of accents, spelling, and non-Latin characters.
• You need a separate video for each language: use the multilingual video editions workflow. That serves a different goal from mixing languages inside one continuous video.

Related Golpo guides

• Prompt Mode vs Script Mode — choose who writes the narration and review the input controls.
• Every Golpo Canvas style — compare Compact, Expanded, and Notebook visual layouts.
• Use only script words for on-screen text — understand the separate display-text control.
• Video Instructions — direct drawings and labels without putting those directions into the narration.
• Voice Instructions — guide tone, pace, and emphasis.
• Map sentences to scenes — plan visual changes before production.
• Create separate multilingual video editions — prepare localized outputs when each audience needs its own video.