messages listlengths 3 3 |
|---|
[
{
"role": "system",
"content": "You are a YouTube scriptwriter. Write the full narration script for a video based on the user's prompt. Write only the narration — no stage directions, scene headings, or visual descriptions. Just the words that would be spoken."
},
{
"role": "user",
"content": "W... |
[
{
"role": "system",
"content": "You are a YouTube scriptwriter. Write a detailed video script based on the user's prompt. For each scene, provide the narration (the exact words spoken) and a visual description (what is shown on screen). Format each scene with NARRATION: and VISUAL: labels."
},
{
"ro... |
[
{
"role": "system",
"content": "You are a YouTube scriptwriter. Write the full narration script for a video based on the user's prompt. Write only the narration — no stage directions, scene headings, or visual descriptions. Just the words that would be spoken. Begin your response with a TITLE: line containi... |
[
{
"role": "system",
"content": "You are a YouTube scriptwriter. Write a detailed video script based on the user's prompt. For each scene, provide the narration (the exact words spoken) and a visual description (what is shown on screen). Format each scene with NARRATION: and VISUAL: labels. Begin your respon... |
[
{
"role": "system",
"content": "You are a YouTube scriptwriter. Write the full narration script for a video based on the user's prompt. Write only the narration — no stage directions, scene headings, or visual descriptions. Just the words that would be spoken."
},
{
"role": "user",
"content": "W... |
[
{
"role": "system",
"content": "You are a YouTube scriptwriter. Write a detailed video script based on the user's prompt. For each scene, provide the narration (the exact words spoken) and a visual description (what is shown on screen). Format each scene with NARRATION: and VISUAL: labels."
},
{
"ro... |
[
{
"role": "system",
"content": "You are a YouTube scriptwriter. Write the full narration script for a video based on the user's prompt. Write only the narration — no stage directions, scene headings, or visual descriptions. Just the words that would be spoken. Begin your response with a TITLE: line containi... |
[{"role":"system","content":"You are a YouTube scriptwriter. Write a detailed video script based on (...TRUNCATED) |
[{"role":"system","content":"You are a YouTube scriptwriter. Write the full narration script for a v(...TRUNCATED) |
[{"role":"system","content":"You are a YouTube scriptwriter. Write a detailed video script based on (...TRUNCATED) |
End of preview. Expand in Data Studio
Disturban scripts
This dataset contains scripts from the YouTuber Disturban.
The records were parsed with Gemini 3 Flash to generate both voiceover text and video descriptions, so this dataset is not just audio transcripts. It is structured for workflows that need paired narration and visual-scene descriptions.
Files
disturban.jsonl: JSONL records containing parsed Disturban script content and generated descriptions.
Possible uses
- Narration-to-video or script-to-shot-description modeling
- Video planning and storyboarding experiments
- Long-form script analysis
- True-crime content structure analysis
Content warning
Disturban content often covers crime, violence, disturbing events, and other sensitive topics. Downstream users should expect potentially graphic or distressing subject matter.
- Downloads last month
- 41