DemonGatanjieuandClaude Opus 5.5
d69507724e
Assigning a voice used to mean selecting a line card and then clicking a voice row in the studio behind the drawer, which was not discoverable. - pick one character at the top (F5-TTS needs one main voice per script); the hint lists the emotions that character can voice - after parsing, each line is a card with editable text, a preview button, delete, and a row of emotion chips (main / happy / ...); a choice the current character cannot voice stays visible and blocks the bundle instead of being silently reset - the footer shows the bundled speech and offers copy, push to the selected or only F5TTSAudio node, and a handle to drag the bundle onto a node - voice rows and the bundle both use the shared bindMaterialDrag (the browser hides while dragging, the target node is highlighted); the studio's own window drop listener and the row-click assignment path are removed - bundling is pure (buildScriptPackage/usableEmotions in audio_script.js) Verified: tests/audio_script_rules.mjs, jsdom walkthrough of parse -> chips -> push -> character switch -> drag onto a node, domain navigation walkthrough; other JS tests unchanged. Not yet checked in a live ComfyUI session. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W411Z69FC3em9CzpeqEub5
67 lines
2.8 KiB
JavaScript
67 lines
2.8 KiB
JavaScript
/**
|
|
* Pure rules for ComfyUI-F5-TTS voices (no DOM, no canvas access).
|
|
*
|
|
* F5-TTS multi-voice layout: the node's `sample` is a main voice such as
|
|
* `F5-TTS/Arona.wav`; `{happy}` in the speech loads `F5-TTS/Arona.happy.wav`
|
|
* beside it, and `{main}` is the sample itself. Speech is split only at tags.
|
|
*/
|
|
|
|
export const MAIN_TAG = '{main}';
|
|
|
|
const normalisePath = value => String(value ?? '').replace(/\\/g, '/');
|
|
|
|
/** Return the widget's own spelling of `relativePath` (Windows combos use "F5-TTS\\x.wav"), or null when not offered. */
|
|
export function comboValueForPath(widget, relativePath) {
|
|
const wanted = normalisePath(relativePath);
|
|
if (!wanted) return null;
|
|
const values = Array.isArray(widget?.options?.values) ? widget.options.values : null;
|
|
if (!values) return wanted;
|
|
return values.find(value => normalisePath(value) === wanted) ?? null;
|
|
}
|
|
|
|
/** Split on sentence punctuation and newlines; '.' only ends a line before whitespace (keeps 3.5). */
|
|
export function splitScriptLines(text) {
|
|
return String(text || '')
|
|
.split(/\n+|(?<=[。！？!?…])|(?<=\.)(?=\s)/)
|
|
.map(line => line.trim())
|
|
.filter(Boolean);
|
|
}
|
|
|
|
/** Once any line is tagged, untagged lines get {main} instead of inheriting the previous voice. */
|
|
export function composeScript(lines) {
|
|
const anyTagged = lines.some(line => line.voice?.tag);
|
|
return lines
|
|
.map(line => {
|
|
const tag = line.voice?.tag || (anyTagged ? MAIN_TAG : '');
|
|
return tag ? `${tag} ${line.text}` : line.text;
|
|
})
|
|
.join('\n')
|
|
.trim();
|
|
}
|
|
|
|
/** Emotions of a voice group that F5-TTS can load as `{emotion}` (main first). */
|
|
export function usableEmotions(group) {
|
|
return (group?.slices || []).filter(slice => slice.tag_usable).map(slice => slice.emotion);
|
|
}
|
|
|
|
/**
|
|
* Bundle script lines for one F5TTSAudio node. `lines` are `{ text, emotion }`;
|
|
* the node's sample becomes the group's main voice and every emotion must be a
|
|
* usable variant of that group. Returns `{ sample, speech, lineCount }` or `{ error: localeKey }`.
|
|
*/
|
|
export function buildScriptPackage(lines, group) {
|
|
if (!group) return { error: 'scriptDirectorPickCharacter' };
|
|
const usable = new Set(usableEmotions(group));
|
|
if (!group.main_relative_path || !usable.has('main')) return { error: 'scriptDirectorMainMissing' };
|
|
const voiced = [];
|
|
for (const line of lines || []) {
|
|
const text = String(line?.text || '').trim();
|
|
if (!text) continue;
|
|
const emotion = line.emotion || 'main';
|
|
if (!usable.has(emotion)) return { error: 'scriptDirectorVoiceUnusable' };
|
|
voiced.push({ text, voice: emotion === 'main' ? null : { tag: `{${emotion}}` } });
|
|
}
|
|
if (!voiced.length) return { error: 'scriptDirectorEmpty' };
|
|
return { sample: group.main_relative_path, speech: composeScript(voiced), lineCount: voiced.length };
|
|
}
|