Menu
Use when someone wants a multi-part story with voiceover โ episodic B-roll, chaptered promo, or several linked video scenes without on-camera dialogue.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when someone needs spoken narration or voiceover โ explainer tracks, documentary lines, or voice to pair with generated video.
Use when someone wants an original AI song with vocals โ sung lyrics, a style prompt track, or source audio for a music video.
Use when someone wants light instrumental background music โ an ambient bed under dialogue or underscore for reels and explainers.
Use when someone needs word-level timestamps from audio โ lyric alignment, cut-safe line boundaries, or caption source timing before burn-in with video-editing.
Use when crafting TTS, music, or bed prompts for any generative audio model โ director style, song structure, and post-production layering.
Use when applying official Pruna brand assets โ logo selection, colors, and overlay rules for launches, social, and video.
| name | narrated-multi-scene |
| description | Use when someone wants a multi-part story with voiceover โ episodic B-roll, chaptered promo, or several linked video scenes without on-camera dialogue. |
| license | MIT |
| metadata | {"version":"1.0.8","package":"pruna-skills"} |
Install and load these skills before generating (skip if already in context via @pruna):
| Skill | Description | Install |
|---|---|---|
p-image | Use when someone wants a fast AI image โ product shots, hero visuals, mood boards, or draft photos from a text prompt. | npx skills add PrunaAI/pruna-skills@p-image -y |
p-image-edit | Use when someone wants to edit an existing photo โ change outfits or backgrounds, compose from reference images, or apply prompt-driven edits. | npx skills add PrunaAI/pruna-skills@p-image-edit -y |
p-video | Use when someone wants one short video clip from text or images โ B-roll, start/end frame animation, or a quick motion shot. Not for full multi-scene films or lip-synced hosts. | npx skills add PrunaAI/pruna-skills@p-video -y |
gemini-3.1-flash-tts | Use when someone needs spoken narration or voiceover โ explainer tracks, documentary lines, or voice to pair with generated video. | npx skills add PrunaAI/pruna-skills@gemini-3.1-flash-tts -y |
stable-audio-2.5 | Use when someone wants light instrumental background music โ an ambient bed under dialogue or underscore for reels and explainers. | npx skills add PrunaAI/pruna-skills@stable-audio-2.5 -y |
Or install the full suite once: npx skills add PrunaAI/pruna-skills@pruna -y
Follow each skill's Before generating / craft sections โ do not restate guide content here.
In every reply, name `narrated-multi-scene` in backticks. State phase gates using exact phrases approve plan, approve stills, approve clips (user types these to proceed). Do not same-turn plan + paid video. Skip-review / burn-credits โ follow generation-diversity Red flags.
| Phase | What to show | Proceed when |
|---|---|---|
| 0 โ Plan | Scene table, narration lines, style_bible | approve plan |
| A โ Stills | Hero + start/end stills per scene | approve stills |
| A2 โ TTS | audio/narration_*.mp3 per scene โ listen | Lines OK (ffprobe โค ~19s) |
| B โ Video | p-video clips with embedded VO | approve clips |
| D โ Bed | Optional Stable Audio under concat | User accepts |
Execute phases with parallel curl batches โ never batch p-video before still and TTS review.
Open intake โ generation-diversity clarification intake.
Do not start scene 1 until the whole scene plan exists in writing (manifest or table):
| Topic | Questions |
|---|---|
| Story | Order of scenes (1โฆN)? What changes between scenes (location, time, emotion)? |
| Media source | Per scene: generate stills/TTS with Pruna tools vs upload user frames or VO? |
| Format | Global aspect_ratio; default video 720p / 1080p and fps for triple scenes? |
| Per scene i | Primary prompt? First frame (image), last frame (last_frame_image), narration (audio URL)? Scene-level resolution / fps / draft overrides? |
| Continuity | Per scene: chain_from_previous only when motion continues (same moment/location). Otherwise composed OPENING still + hard cut. End stills via p-image-edit; extract last frame when chaining. |
| Audio | Scene anchor triple (preferred): TTS โ upload โ p-video with image + last_frame_image + audio (omit duration; save_audio: true). Each scene line โค ~19s โ P-API caps audio-led clips at 20s. Optional Stable Audio bed in post only. |
| Visual style | Locked style_bible? One specific subject/location per still? Avoid unrelated branding unless the brief asks for it |
| Global | Default aspect_ratio for text-only scenes? Global seed policy? |
| Runtime | Target total duration after assembly? |
| Assembly | Concat order; narration mux; bed mix volume (~0.08โ0.15 under VO)? |
Ask follow-ups until every scene row has enough to build input without guessing.
# | Prompt | First frame (image) | Last frame (last_frame_image) | Narration (audio) | Mode |
|---|---|---|---|---|---|
| 1 | motion prompt | start still | end still โ scene 2 | TTS line โ upload | triple |
| 2 | = scene 1 end | end still โ scene 3 | TTS line โ upload | triple |
Mode: T2V ยท I2V ยท I2V+last ยท triple (image + last_frame_image + audio โ omit duration)
p-image-edit start/end stills (pruna-api parallel batches) โ approve stills.p-video triples once all anchors ready โ approve clips.p-image or upload.p-image-edit per scene โ start still (edit_prompt) from hero; end still (last_frame_edit_prompt) from start still. Parallel after hero exists.chain_from_previous: true only when scene i continues directly from iโ1. Use composed start still + hard cut for new beats.gemini-3.1-flash-tts per scene โ upload each to /v1/files.
Duration gate (required):
ffprobe -v error -show_entries format=duration -of csv=p=0 audio/narration_01.mp3
If any scene exceeds ~19s, fix before p-video โ output truncates at the 20s API max even when input.audio is set.
If a line is too long (pick one or combine):
| Remedy | When | Action |
|---|---|---|
| Shorten copy | One beat has too many facts | Cut clauses; keep dates/names; target โค ~45 words (~17โ18s) per scene |
| Faster pace | Line is right length but slow delivery | Tighten Gemini style_prompt (e.g. ~2.3 words/sec, brisk, no filler); regenerate TTS only |
| Split scene | Two story beats in one row | Add scene row + edit_prompt / last_frame_edit_prompt / narration; one MP3 per row |
Scene anchor triple โ one p-video job per row:
{
"prompt": "...",
"image": "START_URL",
"last_frame_image": "END_URL",
"audio": "NARRATION_URL",
"resolution": "720p",
"fps": 24,
"save_audio": true
}
Omit duration. Always include uploaded audio in input. Poll all get_url until done; retry failed scenes only. Parallel pattern: pruna-api.
Adjust prompt, stills, or narration; re-run that scene only.
Hard-cut concat (narration already embedded):
# clips.txt: file 'clips/01.mp4'\nfile 'clips/02.mp4' โฆ
ffmpeg -y -f concat -safe 0 -i clips.txt -c copy film.mp4
Optional short crossfade between chained scenes (~0.15s) โ use xfade / acrossfade when joins need softness; hard-cut elsewhere.
Optional bed โ stable-audio-2.5 under VO:
ffmpeg -y -i film.mp4 -i bed.mp3 \
-filter_complex "[1:a]volume=0.12[bed];[0:a][bed]amix=inputs=2:duration=first[a]" \
-map 0:v -map "[a]" -c:v copy -c:a aac film_with_bed.mp4
Scene table + all six URLs per scene (start, end, audio in/out) + prediction ids.
Scene 1: composed start, last=play_end, audio=vo_1 chainโ2
Scene 2: extract(clip_1), last=loss_end, audio=vo_2 hard cutโ3
Scene 3: composed start, last=search_end, audio=vo_3 chainโ4
Scene 4: extract(clip_3), last=tree_end, audio=vo_4 chainโ5
Scene 5: extract(clip_4), last=reunion, audio=vo_5
See video-prompting for when to chain vs hard cut, and OPEN/MID/CLOSE prompt structure.
Related skills:
| Skill | Description | Install |
|---|---|---|
image-to-video | Use when someone wants one short film beat from images โ a narrated scene, story moment, or cinematic B-roll with optional voiceover. | npx skills add PrunaAI/pruna-skills@image-to-video -y |
avatar-multi-scene | Use when someone wants the same person hosting several clips โ multi-segment UGC, comparison reels, or mixed speaking and animated scenes with continuity. | npx skills add PrunaAI/pruna-skills@avatar-multi-scene -y |
audio-prompting | Use when crafting TTS, music, or bed prompts for any generative audio model โ director style, song structure, and post-production layering. | npx skills add PrunaAI/pruna-skills@audio-prompting -y |
pruna-api | Use before any Pruna or Replicate HTTP call โ credentials, upload/poll/download, parallel batches, and agent safety. | npx skills add PrunaAI/pruna-skills@pruna-api -y |
video-editing | Use when assembling or polishing already-rendered clips with ffmpeg โ concat, crossfades, burned captions and subtitles, text/logo overlays, before/after sliders, background music beds, platform export โ or when composing a multi-layer HTML combination video with Hyperframes. Not for AI video generation, prompt craft, or model-based video edits. | npx skills add PrunaAI/pruna-skills@video-editing -y |