@gentbajko/slopify 3.18.2 → 3.20.0

package/dist/slices/rebuild/preview-details.js

@@ -159,6 +159,8 @@ function inputChanges(parent, view) {
     add("Show tables and figures on screen", before.showFigures === true ? "On" : "Off", after.showFigures === true ? "On" : "Off");
     add("Pause between sentences (seconds)", before.sentencePauseSeconds ?? 0, after.sentencePauseSeconds ?? 0);
     add("Pause between paragraphs (seconds)", before.paragraphPauseSeconds ?? 0, after.paragraphPauseSeconds ?? 0);
+    add("Soften breaths", before.removeBreaths === true ? "On" : "Off", after.removeBreaths === true ? "On" : "Off");
+    add("Soften S sounds", before.deEss === true ? "On" : "Off", after.deEss === true ? "On" : "Off");
     add("Level the volume", before.loudness === undefined ? "Off" : loudnessSummary(before.loudness), after.loudness === undefined ? "Off" : loudnessSummary(after.loudness));
     add("YouTube description", before.youtubeDescription === true ? "On" : "Off", after.youtubeDescription === true ? "On" : "Off");
     add("Description prompt", before.descriptionPrompt, after.descriptionPrompt);

package/dist/slices/rebuild/recipe-audio.js

@@ -5,6 +5,7 @@ import { concatArgs } from "../narration/concat.js";
 import { normalizeNarrationText } from "../narration/plan.js";
 import { pronunciationChunks } from "../narration/pronunciation-chunks.js";
 import { aliasFutureValues, narrationParts, pronunciationFutureValues, voiceValues, } from "./recipe-audio-parts.js";
+import { breathValues } from "./recipe-breaths.js";
 import { levelRecipe } from "./recipe-loudness.js";
 import { recipe, resourceIdentity, selectedReference, } from "./recipe-model.js";
 import { narrationFileRecipe } from "./recipe-narration-text.js";
@@ -142,6 +143,7 @@ export function audioRecipes(context, text) {
                     : (config.chunking ?? defaultChunking).mode === "paragraph"
                         ? "paragraph"
                         : "sentence")),
+                ...breathValues(config),
             ],
         }, parts.map((part) => part.key), { unresolved: text.narrationText !== null && groups.length === 0 });
         recipes.push(body);
@@ -199,6 +201,7 @@ export function audioRecipes(context, text) {
                 parts.map((part) => resourceIdentity(context, part)),
                 parts.length === 1 ? "copy-single-file" : concatArgs("$parts", "$output"),
                 ...pauseValues(config, parts.map((_part, at) => (at === parts.length - 1 ? "end" : "sentence"))),
+                ...breathValues(config),
             ],
         }, parts.map((part) => part.key));
         recipes.push(audio);

package/dist/slices/rebuild/recipe-breaths.js

@@ -0,0 +1,26 @@
+import { breathsOn, deEsser, deEssOn } from "../narration/breaths-model.js";
+// Soften breaths and Soften S sounds (`narration/breaths-model.ts`) are made in the narration
+// joins, so a join carries them in its values, after the pauses when they are set. Nothing at
+// all while they are off, so every join made before them keeps its fingerprint. The levelled
+// join copies these values, so it softens the same.
+// v2: 3.19.0's v1 muted breaths to silence and could clip word edges; its joins are remade.
+export const breathsValue = "breaths-v2";
+export const deEssValue = "deess-v1";
+export function breathValues(config) {
+    return [
+        ...(breathsOn(config) ? [[breathsValue]] : []),
+        ...(deEssOn(config) ? [[deEssValue, deEsser.intensity, deEsser.max, deEsser.frequency]] : []),
+    ];
+}
+// Whether a join's values ask for it: any value after the join's own two.
+export function breathsAsked(values) {
+    return laterValues(values).some((value) => value.length === 1 && value[0] === breathsValue);
+}
+export function deEssAsked(values) {
+    return laterValues(values).some((value) => value[0] === deEssValue);
+}
+function laterValues(values) {
+    return Array.isArray(values)
+        ? values.slice(2).filter((value) => Array.isArray(value))
+        : [];
+}

package/dist/slices/rebuild/recipe-voices.js

@@ -9,6 +9,7 @@ import { prepareRequests } from "../narration/steering.js";
 import { groupTurns } from "../voices/grouping.js";
 import { speakerPace } from "../voices/model.js";
 import { parseScript } from "../voices/script.js";
+import { breathValues } from "./recipe-breaths.js";
 import { describedText, describeFuture, describing } from "./recipe-describe.js";
 import { recipe, resourceIdentity, } from "./recipe-model.js";
 import { pauseValues } from "./recipe-pauses.js";
@@ -125,6 +126,7 @@ export function voiceBodyRecipes(context, voices, script, glossary) {
             layout,
             // Pauses between sentences inside a turn; the turn gap stays the layout's.
             ...pauseValues(context.config, layout.map(([, gap], at) => at === layout.length - 1 ? "end" : gap > 0 || turnEnds.has(at) ? "turn" : "sentence")),
+            ...breathValues(context.config),
         ],
     }, parts.map((part) => part.key), { unresolved: parsed?.ok !== true || pending });
     return {

package/dist/slices/rebuild/runtime-local.js

@@ -5,12 +5,14 @@ import { referenceKey, thumbnailVariant } from "../admission/model.js";
 import { plainText } from "../article/plain.js";
 import { splitEndMatter } from "../article/split.js";
 import { levelPieces } from "../loudness/level-pieces.js";
+import { cleanPieces } from "../narration/clean-pieces.js";
 import { joinNarration } from "../narration/concat.js";
 import { applyPauses, planPieces } from "../narration/pauses.js";
 import { allocateAsset, discardPreparedAssets, sealAsset } from "../storage/assets.js";
 import { outputPath } from "../storage/layout.js";
 import { probeDurationMs, runFfmpeg } from "../video/ffmpeg.js";
 import { turnJoinArgs } from "../voices/join.js";
+import { breathsAsked, deEssAsked } from "./recipe-breaths.js";
 import { levelOperation } from "./recipe-loudness.js";
 import { executeFigureCard } from "./runtime-figure-card.js";
 import { publishNarrationText } from "./runtime-narration-text.js";
@@ -134,16 +136,28 @@ async function concatenate(deps, context, piece) {
     try {
         const run = { bin: deps.ffmpeg, log: deps.log, signal: context.signal };
         const levelled = level ? await levelPieces(run, files, piecesDirectory) : undefined;
+        // Soften breaths, then Soften S sounds: made in what is joined, before the pauses; nothing
+        // moves, so the pauses are still planned from the pieces as spoken.
+        const cleaned = await cleanPieces(run, levelled?.files ?? files, piecesDirectory, {
+            breaths: breathsAsked(values),
+            deEss: deEssAsked(values),
+        });
+        if (cleaned?.breaths !== undefined)
+            deps.log.write("info", "narration.breaths", {
+                projectId: context.work.projectId,
+                stage: "audio",
+                detail: `${String(cleaned.breaths.softened)} breaths softened, ${String(cleaned.breaths.skipped)} left alone (a word sound in them) in ${String(files.length)} pieces`,
+            });
         // Pauses between sentences: planned from the pieces as spoken, made in what is joined.
         const pauses = pausesIn(values);
         const paced = pauses === undefined
             ? undefined
-            : await applyPauses(run, levelled?.files ?? files, paceScaled(await planPieces(run, files.map((file, at) => ({
+            : await applyPauses(run, cleaned?.files ?? levelled?.files ?? files, paceScaled(await planPieces(run, files.map((file, at) => ({
                 file,
                 text: pieceText(plan.recipes.find((one) => one.key === recipe.dependsOn[at])),
                 next: pauses.next[at] ?? "end",
             })), pauses.settings), operation === "concat-turns-v1" ? values : undefined), join(piecesDirectory, "paced"));
-        const joined = paced?.files ?? levelled?.files ?? files;
+        const joined = paced?.files ?? cleaned?.files ?? levelled?.files ?? files;
         const durationMs = operation === "concat-turns-v1"
             ? await joinTurns(run, joined, values, pending.absolutePath)
             : await joinNarration({ bin: deps.ffmpeg, log: deps.log }, {
@@ -151,7 +165,7 @@ async function concatenate(deps, context, piece) {
                 output: pending.absolutePath,
                 listPath: join(dirname(pending.absolutePath), "parts.txt"),
                 signal: context.signal,
-                reencode: level || paced !== undefined,
+                reencode: level || paced !== undefined || cleaned !== undefined,
             });
         rmSync(piecesDirectory, { recursive: true, force: true });
         context.signal.throwIfAborted();

package/dist/tutorials/Editing-a-Project.md

@@ -128,12 +128,14 @@ See [Narration Aliases and Glossary](Narration-Aliases-and-Glossary).
 
 ## Pauses and volume
 
-**Edit project → Inputs → Pauses and volume** holds four settings. All run on your computer with no API calls.
+**Edit project → Inputs → Pauses and volume** holds these settings. All run on your computer with no API calls.
 
 | Option | What it does | Default / range |
 | --- | --- | --- |
 | **Pause between sentences (seconds)** | The least quiet after each sentence. Adds silence where the pause is shorter; never shortens one or cuts a word. About 0.25 s is brisk, 0.35 to 0.45 natural, 0.5 to 0.8 an audiobook's pace, 0.8 and up sleep content. 0 keeps the voice's own. | 0.4; 0 to 2 in steps of 0.05 |
 | **Pause between paragraphs (seconds)** | The least quiet at the end of a paragraph, when you want more than between sentences. At 0 paragraphs get the sentence pause. Try 0.8 to 1.2 for a slower read. A speaker's turn gap is set under Speakers instead. | 0; 0 to 2 |
+| **Soften breaths** | Turns the audible in-breaths a voice takes between sentences and after commas down by 12 dB, with soft fades (Inworld's TTS-2 takes a loud one almost every time). A breath with any word sound in it is left alone; words, pauses and captions stay where they were. | Off |
+| **Soften S sounds** | Takes the sharp edge off s and sh sounds with a very light de-esser; the voice keeps its brightness. Works with or without Soften breaths. | Off |
 | **Level the volume** | Brings every narration piece to one loudness before they are joined, then sets the video, shorts and audio files to a finished loudness. | On for new runs (Settings → General → **Level the volume for new runs**) |
 | **Video volume** | How loud the video and shorts are, in dB from the recommended level (0 dB is -14 LUFS, what YouTube and Spotify play at). -6 dB is about 50%, +4 dB about 158%. Peaks stay under -1.5 dBTP. | 0 dB; -10 to +4 dB in 0.5 dB steps |
 | **Audio files volume** | How loud the WAV, MP3 and M4B are, in dB from -18 LUFS (what audiobook shops such as ACX ask for). Peaks stay under -3 dBTP. | 0 dB; -10 to +4 dB |
@@ -142,7 +144,7 @@ You can type a volume in dB or as a percentage of the recommended level.
 
 What changing them remakes:
 
-- **Pauses**: the narration is joined again from the pieces it already has and timed again, which remakes what is timed from it: captions, the video and, when on, the YouTube description and the shorts' pick (those two are text calls). No speech is made again.
+- **Pauses, Soften breaths or Soften S sounds**: the narration is joined again from the pieces it already has and timed again, which remakes what is timed from it: captions, the video and, when on, the YouTube description and the shorts' pick (those two are text calls). No speech is made again.
 - **Level the volume on or off**: the levelled narration is joined again and the exports rendered again. No speech is made again, and word timing, description, shorts' pick and reviews are not redone.
 - **A volume only**: the exports are mastered again, nothing else.