移除 TTS 阶段逐句切分及 segments 数组逻辑,统一为整段音频合成。 CapCut 字幕切分由组装阶段按字符比例分配,简化音频上传、 时间线构建和字幕生成流程,减少冗余处理分支。
54 lines
1.8 KiB
JavaScript
54 lines
1.8 KiB
JavaScript
/**
|
||
* Phase: tts — 语音合成(整段合成)
|
||
*
|
||
* 每个 item 的 script 整段合成一个音频文件,保留自然语调。
|
||
* item.audio 指向完整音频,item.audioDuration 为总时长。
|
||
* 字幕切分由组装阶段按字符比例分配,不在 TTS 阶段处理。
|
||
*/
|
||
|
||
const path = require('path')
|
||
const { saveManifest, ensureDir, log, getManifestDir } = require('./pipeline-utils')
|
||
|
||
async function phaseTts(manifest, manifestPath, options = {}) {
|
||
const dir = getManifestDir(manifestPath)
|
||
const audioDir = path.join(dir, 'audio')
|
||
ensureDir(audioDir)
|
||
|
||
const { synthesize } = require('../qwen-tts')
|
||
|
||
const items = manifest.items.filter(it =>
|
||
it.status === 'done' && (it.script || it.text) && !it.audio
|
||
)
|
||
if (items.length === 0) { log('tts', '无待处理 item,跳过'); return }
|
||
|
||
log('tts', `共 ${items.length} 段`)
|
||
|
||
for (let i = 0; i < items.length; i++) {
|
||
const item = items[i]
|
||
const idx = i + 1
|
||
const fullText = item.script || item.text
|
||
|
||
try {
|
||
const { filePath, duration } = await synthesize(fullText, {
|
||
outputDir: audioDir,
|
||
id: String(item.id || idx),
|
||
voice: manifest.ttsVoice || undefined,
|
||
instruction: manifest.ttsInstruction || undefined,
|
||
rate: manifest.ttsRate || undefined,
|
||
})
|
||
|
||
const totalDuration = Math.round(duration * 1000) / 1000
|
||
item.audio = path.relative(dir, filePath).replace(/\\/g, '/')
|
||
item.audioDuration = totalDuration
|
||
log('tts', `[${idx}/${items.length}] ${totalDuration.toFixed(1)}s: ${fullText.substring(0, 30)}...`)
|
||
} catch (err) {
|
||
item.status = 'failed'
|
||
item.error = `TTS失败: ${err.message}`
|
||
log('tts', `[${idx}/${items.length}] 失败: ${err.message}`)
|
||
}
|
||
saveManifest(manifestPath, manifest)
|
||
}
|
||
}
|
||
|
||
module.exports = { phaseTts }
|