import { t } from './interface_settings.js'; import { anomalousAlert } from './ui_dialog.js'; import { buildTtsPrompt, TTS_NODE_CLASS } from './audio_script.js'; import { startPromptJob } from './audio_tts_run.js'; import { fetchGptSovitsCharacter, loadGptSovitsStatus, saveGptSovitsSettings } from './audio_engines.js'; import { PRESETS_FORMAT, SAMPLE_LINES, lineTuning, loadPresets, presetLabel, presetsFile, savePresets, stateFromView, tuningRows, } from './tts_presets_api.js'; import { AUTO_MODE, LINE_TAGS_FORMAT, TUNE_FIELDS, characterLayer, clearLineTune, lineLayer, lineValues, scriptLayer, setLineTune, setOwn, tuneTags, } from './script_tune.js'; import { keepParamFocus } from './ui_tts_preset_switch.js'; import { createModePreview } from './ui_tts_mode_preview.js'; import { openTtsSetup } from './ui_tts_setup.js'; import { openTuningEditor } from './ui_tts_tuning.js'; import { LANGUAGES, renderTunePanel } from './ui_script_tune.js'; /** * The Script Director's "Generate" section for GPT-SoVITS characters: runs the * script through ComfyUI's queue (audio_tts_run.js) without touching the canvas, * plays the result, and offers another take of the whole script (new seed) or of * one line (`[take:N]`, the other lines come from the node's cache). * * How each line is read: its language, speed and tone in three layers changed for this script * (script_tune.js): the line, its character (kept here), the whole script (kept here); then the * character's usual `defaults` (language and speed, which can be saved back) and the usual tone * (the presets and the character's own settings decide line by line). The side panel showing * them follows what is picked on the left (ui_script_tune.js). Anomalous_TTS interface 17 gets * the whole script's values through the node's inputs and the rest as tags on the lines that * need them; an older node reads the whole script with the first line's character's values * through its inputs. The tones can be heard on a line (ui_tts_mode_preview.js); a preset's * numbers changed here are saved into that preset. * * The director owns the lines; this section owns the job, the characters' values and the * result, which live for the page session like the director's panel. It has two parts that * the director places together: `bar` (generate / retake / cancel and the result, with a way to * the audio gallery) and `settings` (the side panel). */ const MIN_FORMAT = 11; // Anomalous_TTS interface with [take:N] and `defaults` const NUMBERS = ['speed']; function el(tag, className, text) { const node = document.createElement(tag); if (className) node.className = className; if (text !== undefined) node.textContent = text; return node; } function button(className, label, onClick, title) { const btn = el('button', className, label); btn.type = 'button'; if (title) btn.title = title; btn.onclick = onClick; return btn; } function newSeed() { return Math.floor(Math.random() * 2 ** 31); } function audioUrl(audio) { const query = new URLSearchParams({ filename: audio.filename, subfolder: audio.subfolder || '', type: audio.type || 'output' }); return `/view?${query}`; } /** `{ speed: { default, min, max, step } }` from ComfyUI's description of the node. */ async function loadNodeSpec() { const resp = await fetch(`/object_info/${TTS_NODE_CLASS}`); const info = (await resp.json())?.[TTS_NODE_CLASS]?.input || {}; const inputs = { ...(info.required || {}), ...(info.optional || {}) }; const spec = {}; for (const name of NUMBERS) { const options = inputs[name]?.[1]; if (options && typeof options.default === 'number') spec[name] = options; } return spec; } /** * `getScript()` -> `{ group, lines, listen, speakerOf, pkg, groups, picked, focus, assign, focusCharacter, * focusScript }` (the node's character = the first line's, the director's lines, the one to listen * with, who reads a line, pkg from buildScriptPackage with takes, the characters, the picked line * indexes, the character shown, and the director's calls); `getNodeGroup()` -> the node's character * alone (the tags need it, and getScript builds the tagged script); `getGroups()` -> every voice group (for * the presets' "used by"); `onPlay()` when the result starts playing; `resetTakes()` when a new take * of the whole script starts; `onBusyChange()` when a job starts or ends (the director re-renders its * line cards, whose retake buttons depend on it); `onLinesChange()` after a line's values changed (the * cards' tags); `openGallery()` for the result's "saved to the audio gallery". */ export function createRunSection({ getScript, getNodeGroup, getGroups, onPlay, resetTakes, onBusyChange, onLinesChange, openGallery }) { const state = { seed: newSeed(), spec: null, // node input ranges/defaults; null until loaded presets: null, // loadPresets(); null without interface 16 format: 0, // the node's interface local: false, // this computer (presets can be changed) script: {}, // the whole script's values changed here (only the fields set) cast: new Map(), // character -> its values changed here for this script (only the fields set) settings: new Map(), // character -> its settings as saved in this session saved: new Map(), // character -> options saved in this session savedNow: null, // the character just saved ("Saved" on its button for a moment) saving: false, presetNote: '', job: null, status: null, // { state: 'queued' | 'running' | 'done' | 'cancelled', value?, max?, seconds? } result: null, // { audio, url, warnings, character } supported: null, // TTS interface >= MIN_FORMAT; null while unknown }; const bar = el('div', 'anomalous-sd-run'); const hint = el('div', 'anomalous-sd-run-hint is-warning', t('scriptRunNeedsUpdate')); // How it is read: what is picked on the left (ui_script_tune.js). const settings = el('div', 'anomalous-sd-run-settings'); const actions = el('div', 'anomalous-sd-run-actions'); const generateBtn = button('anomalous-sd-btn accent', t('scriptRunGenerate'), () => generate()); const newTakeBtn = button('anomalous-sd-btn', t('scriptRunNewTake'), () => { state.seed = newSeed(); resetTakes?.(); generate(); }, t('scriptRunNewTakeHint')); const cancelBtn = button('anomalous-sd-btn', t('scriptRunCancel'), () => state.job?.cancel()); const status = el('span', 'anomalous-sd-run-status'); actions.append(generateBtn, newTakeBtn, cancelBtn, status); const player = el('audio', 'anomalous-sd-run-player'); player.controls = true; player.preload = 'auto'; player.addEventListener('play', () => onPlay?.()); const savedTo = button('anomalous-sd-link-btn anomalous-sd-run-saved', t('scriptRunSavedLink'), () => openGallery?.()); const warnings = el('div', 'anomalous-sd-run-warnings'); bar.append(hint, actions, player, savedTo, warnings); const characterSettings = group => state.settings.get(group.character) ?? group?.raw?.settings ?? {}; const preview = createModePreview(() => render()); const canTag = () => state.format >= LINE_TAGS_FORMAT; /** The character's saved language and speed over the node's own defaults; the mode starts on Auto. */ function storedOptions(group) { if (state.saved.has(group.character)) return state.saved.get(group.character); const defaults = characterSettings(group).defaults || {}; return { language: LANGUAGES.includes(defaults.language) ? defaults.language : 'auto', speed: typeof defaults.speed === 'number' ? defaults.speed : state.spec?.speed?.default ?? null, preset: AUTO_MODE, }; } const base = () => ({ language: 'auto', speed: state.spec?.speed?.default ?? 1, preset: AUTO_MODE }); function castOf(group) { if (!state.cast.has(group.character)) state.cast.set(group.character, {}); return state.cast.get(group.character); } /** A character's values in this script with where each comes from; a preset deleted meanwhile reads as the usual tone. */ function layerOf(group) { const layer = characterLayer(castOf(group), state.script, storedOptions(group), base()); if (layer.values.preset !== AUTO_MODE && !state.presets?.presets?.[layer.values.preset]) layer.values.preset = AUTO_MODE; return layer; } const currentOptions = group => (group ? layerOf(group).values : scriptLayer(state.script, base()).values); const sameOptions = (a, b) => a.language === b.language && a.speed === b.speed; const valuesOfLine = line => lineValues(line, currentOptions(getScript().speakerOf(line))); /** * The node's whole-script speed: its input counts only when it differs from the node's default * and from the first character's own speed (Anomalous_TTS reads it that way), else undefined. */ function nodeSpeed() { const speed = state.script.speed; const first = getNodeGroup(); return speed === undefined || speed === base().speed || (first && speed === storedOptions(first).speed) ? undefined : speed; } /** What the node gives a line of `speaker` by itself: the whole script's values as inputs, else the character's own. */ const nodeValues = speaker => ({ language: state.script.language ?? 'auto', speed: nodeSpeed() ?? storedOptions(speaker).speed, preset: state.script.preset ?? AUTO_MODE, }); /** The tags `line` needs (script_tune.js), for the director's packages; none for an older node. */ function tagsOf(line, speaker) { if (!canTag() || !speaker) return ''; return tuneTags(lineValues(line, currentOptions(speaker)), nodeValues(speaker)); } /** The node's inputs for the script: the whole script's values (interface 17), else the first line's character's. */ function scriptInputs(group) { if (!canTag()) { const { language, speed, preset } = currentOptions(group); return { language, speed, ...(state.presets && preset !== AUTO_MODE ? { preset } : {}) }; } const speed = nodeSpeed(); return { language: state.script.language ?? 'auto', ...(speed !== undefined ? { speed } : {}), ...(state.presets && state.script.preset ? { preset: state.script.preset } : {}), }; } /** The language Auto's numbers are shown for: the one chosen, else the character's own. */ function autoKey(group, values) { const refLang = group.raw?.reference?.language || group.language || ''; return values.language !== 'auto' ? values.language : (refLang || 'all'); } /** A mode's four numbers for `group` reading with `values`: Auto's from the presets and its settings. */ function modeNumbers(group, values, id) { if (id !== AUTO_MODE) return state.presets?.presets?.[id]; const refLang = group.raw?.reference?.language || group.language || ''; return lineTuning(state.presets, tuningRows(characterSettings(group)), refLang, autoKey(group, values)).values; } /** * One line read by its character (`speaker`) in tone `mode`, for the listen row and a card's ▶. * With interface 17 the values go as the line's tags (exactly as they will be read), else as inputs. */ function takeFor(line, mode, speaker = null, values = null) { const who = speaker || getScript().speakerOf(line); const own = values || (line ? valuesOfLine(line) : currentOptions(who)); const id = mode ?? own.preset; const words = String(line?.text || '').trim(); const refLang = who.raw?.reference?.language || who.language; const emotion = line?.emotion && line.emotion !== 'main' ? `{${line.emotion}}` : ''; const numbers = modeNumbers(who, own, id); if (canTag()) { const tags = tuneTags({ ...own, preset: id }, { speed: storedOptions(who).speed }); return { character: who.character, text: `${emotion}${tags}${words || SAMPLE_LINES[refLang] || SAMPLE_LINES.zh}`, language: 'auto', mode: id, preset: '', numbers }; } const text = words ? `${emotion}${words}` : SAMPLE_LINES[refLang] || SAMPLE_LINES.zh; return { character: who.character, text, language: own.language, speed: own.speed, mode: id, preset: id, numbers }; } async function reloadPresets() { try { state.presets = await loadPresets(); } catch (_) { /* keep the last ones */ } render(); } async function checkSupport() { try { const [status, spec] = await Promise.all([loadGptSovitsStatus(), loadNodeSpec()]); state.spec = spec; state.format = Number(status?.format) || 0; state.supported = state.format >= MIN_FORMAT && NUMBERS.every(name => spec[name]); state.local = status?.local !== false; if (state.format >= PRESETS_FORMAT) state.presets = await loadPresets(); } catch (_) { state.supported = false; } render(); onBusyChange?.(); // the director draws its cards again, now with their ▶ } /** A preset's number changed here goes into the preset itself, for every character. */ async function editPreset(name, key, value) { const next = stateFromView(state.presets); next.numbers[name][key] = value; try { state.presets = await savePresets(presetsFile(state.presets, next)); state.presetNote = t('scriptRunModeSaved', { name: presetLabel(state.presets.labels, name, t) }); } catch (error) { state.presetNote = t('ttsPresetsSaveFailed', { error: error.message }); } keepParamFocus(settings, render); } async function generate() { const script = getScript(); if (!script?.group || script.pkg.error || state.job || !state.supported) return; const character = script.group.character; const prompt = buildTtsPrompt({ character, speech: script.pkg.speech, seed: state.seed, ...scriptInputs(script.group) }); state.status = { state: 'queued' }; const started = Date.now(); state.job = startPromptJob(prompt, { onStatus: next => { state.status = next; renderStatus(); }, }); onBusyChange?.(); try { const { outputs } = await state.job.result; const audio = outputs['2']?.audio?.[0]; if (!audio) throw new Error(t('scriptRunNoAudio')); // The first line is the node's own count (its sentences, batches, cache), not the reader's lines. const [, ...rest] = String(outputs['1']?.text?.[0] || '').split('\n'); state.result = { audio, url: `${audioUrl(audio)}&t=${Date.now()}`, warnings: rest.filter(Boolean), character }; state.status = { state: 'done', seconds: Math.max(1, Math.round((Date.now() - started) / 1000)) }; state.job = null; onBusyChange?.(); player.play().catch(() => {}); } catch (error) { state.job = null; state.status = error.cancelled ? { state: 'cancelled' } : null; onBusyChange?.(); if (!error.cancelled) await anomalousAlert(t('scriptRunFailed', { error: error.message })); } } async function storeDefaults(group) { const { character } = group; const opts = { ...currentOptions(group) }; state.saving = true; render(); try { // Start from the file as it is now, so edits made elsewhere (the generation settings) are kept. const fresh = await fetchGptSovitsCharacter(character); if (fresh.settings_error) throw new Error(t('scriptRunSettingsBroken', { error: fresh.settings_error })); const saved = { ...(fresh.settings || {}), format: 1 }; // Only what differs from the node's own defaults, so the file stays short. const defaults = { ...(saved.defaults || {}) }; if (opts.language !== 'auto') defaults.language = opts.language; else delete defaults.language; if (opts.speed !== state.spec.speed.default) defaults.speed = opts.speed; else delete defaults.speed; if (Object.keys(defaults).length) saved.defaults = defaults; else delete saved.defaults; await saveGptSovitsSettings(character, saved); state.settings.set(character, saved); state.saved.set(character, { ...opts, preset: AUTO_MODE }); // What was changed for it here is its usual now, unless it still has to go over the whole script's. for (const field of ['language', 'speed']) if (state.script[field] === undefined) delete castOf(group)[field]; state.savedNow = character; setTimeout(() => { state.savedNow = null; render(); }, 1600); } catch (error) { await anomalousAlert(t('scriptRunDefaultsFailed', { error: error.message })); } finally { state.saving = false; render(); } } function saveButton(group) { const label = state.savedNow === group.character ? t('scriptRunDefaultsSaved') : t('scriptRunSaveDefaults'); const btn = button('anomalous-sd-link-btn', label, () => storeDefaults(group), t('scriptRunSaveDefaultsHint')); btn.disabled = state.saving; return btn; } /** The side panel's view of the moment (ui_script_tune.js). */ function renderSettings(script, busy) { const changed = () => { onLinesChange?.(); render(); }; renderTunePanel(settings, { script, view: state.presets, spec: state.spec, busy, local: state.local, canTag: canTag(), presetNote: state.presetNote, preview, redraw: render, options: currentOptions, lineValues: valuesOfLine, layers: { script: () => scriptLayer(state.script, base()), character: layerOf, line: line => lineLayer(line, layerOf(script.speakerOf(line))), }, changedFor: { script: () => TUNE_FIELDS.some(field => state.script[field] !== undefined), character: group => TUNE_FIELDS.some(field => castOf(group)[field] !== undefined), }, setScript: (field, value) => { setOwn(state.script, field, value, base()[field]); state.presetNote = ''; changed(); }, setCharacter: (group, field, value) => { setOwn(castOf(group), field, value, state.script[field] ?? storedOptions(group)[field]); state.presetNote = ''; changed(); }, setLines: (indexes, field, value) => { setLineTune(indexes.map(index => script.lines[index]), field, value, line => currentOptions(script.speakerOf(line))[field]); state.presetNote = ''; changed(); }, clearScript: () => { state.script = {}; changed(); }, clearCharacter: (group) => { state.cast.delete(group.character); changed(); }, clearLines: (indexes) => { clearLineTune(indexes.map(index => script.lines[index])); changed(); }, modeNumbers, autoLanguage: (group, values) => { const key = autoKey(group, values); return key === 'all' ? t('ttsTuningAll') : t(`scriptRunLang_${key}`); }, takeFor, editPreset, canSave: group => state.savedNow === group.character || !sameOptions(currentOptions(group), storedOptions(group)), saveButton, openPresets: () => openTtsSetup({ groups: getGroups?.() || [], showPresets: true, onChanged: reloadPresets }), openTuning: group => openTuningEditor(group, { onSaved: (saved) => { if (saved?.raw?.settings) state.settings.set(group.character, saved.raw.settings); render(); }, }), }); } function renderStatus() { const s = state.status; let text = ''; if (s?.state === 'queued') text = t('scriptRunQueued'); else if (s?.state === 'running') text = s.max ? t('scriptRunProgress', { value: s.value, max: s.max }) : t('scriptRunRunning'); else if (s?.state === 'done') text = t('scriptRunDone', { seconds: s.seconds }); else if (s?.state === 'cancelled') text = t('scriptRunCancelled'); status.textContent = text; status.hidden = !text; } function render() { const script = getScript(); if (state.supported === null) { state.supported = false; checkSupport(); } const { group, pkg } = script; const busy = Boolean(state.job); const ready = Boolean(state.supported && group); hint.hidden = Boolean(state.supported); generateBtn.title = t('scriptRunHint', { character: group?.character || '' }); settings.hidden = actions.hidden = !ready; if (ready) renderSettings(script, busy); generateBtn.disabled = !ready || Boolean(pkg.error) || busy; const hasResult = Boolean(state.result && group && state.result.character === group.character); newTakeBtn.hidden = !hasResult; newTakeBtn.disabled = generateBtn.disabled; cancelBtn.hidden = !busy; renderStatus(); player.hidden = !hasResult; if (hasResult && player.getAttribute('src') !== state.result.url) player.src = state.result.url; savedTo.hidden = !hasResult; if (hasResult) { const folder = String(state.result.audio.subfolder || '').replace(/\\/g, '/'); savedTo.title = `output/${folder}/${state.result.audio.filename}`; } warnings.hidden = !hasResult || !state.result.warnings.length; if (hasResult) warnings.textContent = state.result.warnings.join('\n'); } return { settings, bar, render, generate, tagsOf, /** A card's ▶: its line (the director set it as the one to listen with) as it will be read. */ listen() { const script = getScript(); const line = script?.lines?.[script.listen]; if (!line || !this.canListen()) return; preview.play(takeFor(line)); }, /** Whether the cards show ▶ (the node has modes, a character is chosen, nothing runs). */ canListen() { return Boolean(state.presets && state.supported && !state.job && getScript()?.group); }, /** A line can be retaken once this character has a result and nothing is running. */ canRetake(group) { return Boolean(state.supported && !state.job && state.result && group && state.result.character === group.character); }, /** The presets, for the tags on the cards (ui_script_tune.js ownTuneText). */ presetsView: () => state.presets, /** The whole script's and the characters' values changed here, for the director's draft. */ draft: () => ({ script: { ...state.script }, cast: Object.fromEntries([...state.cast].filter(([, own]) => Object.keys(own).length)) }), /** Another script opened (ui_script_drafts.js): its values, and nothing generated yet. */ restoreDraft({ script = {}, cast = {} } = {}) { state.script = { ...script }; state.cast = new Map(Object.entries(cast).map(([character, own]) => [character, { ...own }])); player.pause(); preview.stop(); state.result = null; state.status = null; }, /** A line is being generated (another script waits until it is done). */ busy: () => Boolean(state.job), stopPlayback() { player.pause(); preview.stop(); }, }; }