One script, two languages: EN and RU versions that match shot for shot
A prompt that writes a script in English and Russian side by side, same shots and same timings, with the Russian rewritten rather than translated so it fits the same seconds.
Write the script below in two languages, English and Russian, as one table: Shot | Seconds | EN line | RU line | On-screen text EN | On-screen text RU. Rules: - Same shots, same seconds in both languages. The visuals are recorded once. - Each RU line must be sayable in the same seconds as the EN line. Russian words are longer, so rewrite the Russian, do not translate it: fewer words, same meaning. Count syllables if in doubt; a parameter to check against is about 4 syllables per second of speech. - Natural spoken Russian, informal address for {audience} unless I say otherwise. No calques from English. - Numbers, product name and URL identical in both. - On-screen text: max 4 words per language. After the table, flag any row where the RU line needed more than {20} percent more syllables than the EN line; I will shorten the shot or the line. Script (EN): {paste script}
In Claude Code, paste the prompt as a message.
Steps
- Write and lock the English version first, with timings. Then run this prompt; the Russian comes out shorter because it has to.
- Record the two voice tracks over one picture. Swap audio with ffmpeg and keep the video stream (`-map 0:v -map 1:a -c:v copy`), one file per language.
- Captions per language go up as separate .srt tracks on YouTube and as separate burned files on feeds.
Tips
- A native speaker reads the RU column once before recording. Models write correct Russian that no one says.
- On-screen text is where language length bites hardest: 'Try it free' is 11 characters; the Russian needs a rewrite, not a translation.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. · Claude: Paste into claude.ai or the Claude app. · ChatGPT: Paste into ChatGPT; works with any GPT model. · Any LLM: Model-agnostic: Gemini, Mistral, a local model. |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | two-language-script-en-ru-prompt.md |
Related
SRT cleanup: fix names from a glossary, merge short cues, cap line length
An agent prompt that takes a raw speech-to-text SRT and returns one you can publish: names fixed from your glossary, sub-second cues merged, lines wrapped at a character cap, timings untouched.
Cut any script to 55 words: the 20-second rewrite prompt
A rewrite prompt that compresses a script to 55 words (about 20 seconds at 165 wpm) without losing the number, the name or the ask, and reports what it removed so you can argue.
Turn a blog post into three short scripts: one claim per video
A prompt that reads a post and returns three 30-45 second scripts, each built on a different claim from the text, with the hook, the proof, the ask and the source sentence for each.
Forced reasoning before scripting: goal, hook type, demo moments, emotion arc
Four questions an agent must answer in writing before it writes a line of script. Skips the generic promo every model produces when asked for one directly.
The 30-45 second promo script: hook, problem, demo, CTA with timings
A fill-in script template for a vertical product promo: four blocks with second counts and a 75-100 word narration budget, so the video ends before the viewer scrolls.
Screen-recording demo script for an app: what to click, what to say, when
A prompt that writes a demo script where every spoken line is paired with one on-screen action, so the recording is done in one pass and the narration recorded over it afterwards.