sk-narration
Writes or edits the spoken script of a short in src/videos/<id>/narration.json, generates the voice track with bun run tts (by default Edge for English, VieNeu for Vietnamese; ElevenLabs optional), and runs the machine lint. Use when the user says "write the script", "change this line", "fix the pronunciation", "it reads too fast", "add a pause", "re-run TTS", "change the voice", or when lint reports narration errors. Also the recorded-voice path (bun run ingest, bun run cut): "use my recording", "make it from my video", "I filmed myself", "transcribe this", "cut the ums", "remove the retake", or a .mov/.mp4/.mp3/.wav file given as the voice. Steps 5, 6 and 7 of sk-pipeline.
howznguyen · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add howznguyen/shorts-kit --skill sk-narration技能说明
name: sk-narration description: Writes or edits the spoken script of a short in src/videos//narration.json, generates the voice track with bun run tts (by default Edge for English, VieNeu for Vietnamese; ElevenLabs optional), and runs the machine lint. Use when the user says "write the script", "change this line", "fix the pronunciation", "it reads too fast", "add a pause", "re-run TTS", "change the voice", or when lint reports narration errors. Also the recorded-voice path (bun run ingest, bun run cut): "use my recording", "make it from my video", "I filmed myself", "transcribe this", "cut the ums", "remove the retake", or a .mov/.mp4/.mp3/.wav file given as the voice. Steps 5, 6 and 7 of sk-pipeline.
sk-narration: script, TTS, lint
Announce: "Using sk-narration for ."
Rules: §1, §3, §3b, §3c (docs/soul/01-voice-and-structure.md), §4
(docs/soul/02-narration-engine.md), the flow file in docs/flows/, numbers in
docs/soul/thresholds.json. The § wins over this file.
Where to edit
Only src/videos/<id>/narration.json (schema in
docs/making-a-video.md). Never hand-edit voice.json: it is generated and
carries a hash of the script it was made from.
A recorded voice (voice.engine: "recorded", §5j)
There is no script to write: the lines come from the recording.
docs/visuals/talking-head.md holds the rules; in short:
bun run ingest <id> <file> --lang <code>; pass--promptwith names and terms said in the take. Read the review it prints.- Edit
cuts.json: fillers, retakes (keep the last attempt), false starts, a call to action at the end (tail). Every cut has a reason; never cut a word to change a sentence's meaning. - Ask the user what was actually said wherever the review shows
?, a number, a name or⟪words missing?⟫. Put each fix inspelling(whole phrase → what was said). Never retypetextand never edittranscript.json. bun run cut <id>, listen topublic/audio/<id>/voice.mp3, then move whole line objects into the flow's beats and addfact(or"claim": false).bun run lint <id>. Writing-style rules only warn here; the fix is a cut or a re-take, not a rewrite.
Steps
- Read the flow file for this video's
flow: its beats become scenes, its "Traps" are mistakes already made once. - Write scene by scene. Each line is one idea; a line stating a fact carries
"fact": "f-xxxx". Hook: a number or claim in the first seconds, without giving away the final answer (§3c). Last line of each scene pulls into the next. End on the turn that negates what the viewer believed, then a share line tied to the content, not a logo or "follow for more" (§1). - Read §3c (tension) before TTS, not after. Re-recording costs more than re-reading.
- Write for the engine (§4).
- Pauses come from full stops. Commas, colons and dashes are nearly silent to TTS engines; where the viewer needs a breath, end the sentence.
- Write numbers the way they should be spoken; put the display form in
spelling(caption-only) and respellings inpronounce(spoken-only). - Silence between lines and scenes comes from
pause.line/pause.scene, not from punctuation tricks.
- Engine default by language (§4, "Pick the engine by language"): when the
user has not chosen an engine, use English →
edge, Vietnamese →vieneu, and say which one you used. It is a default, not a rule: an engine the user picked stays. Ifvieneuis not installed, give them the setup commands from the README. - Generate the voice:
The whole script is read in one pass so intonation carries across sentences; per-line synthesis sounds like a list.bun run tts <id> # whole script in one request, word timestamps bun run tts <id> --force # re-synthesise even if the hash matches - Listen to the whole track. TTS engines can repeat or loop a phrase, and that passes every numeric check. Machines count words; only ears catch rhythm.
- Lint:
0 errors, and read every warning. Duration againstbun run lint <id>maxDurationSecondsandtargetDurationSeconds, sentence length, banned phrases, fact references all come fromthresholds.json.
Rules that bite silently
- Changed
textmeans runbun run tts <id>again. Scene lengths and captions come fromvoice.json; a stale one drifts with no error on screen. - Scene length is never set by hand. It comes from the real voice track.
- On-frame text must not repeat the line being spoken (§7); that is the caption's job.
Verify
-
flowandvisualset; every fact id resolves -
voice.jsonnewer than the last edit tonarration.json - whole track listened to, no loops, numbers pronounced right
-
bun run lint <id>0 errors, warnings read
Next: wording polish with sk-style if lint flags §3b, else sk-scene.