完善音频信息提取能力，优化类型与工程化配置

2025-11-25 03:15:03 +08:00 · 2025-08-04 10:35:26 +08:00
parent 6dad1af850
commit 4c1b8294ea
11 changed files with 139 additions and 23 deletions
--- a/.npmrc
+++ b/.npmrc
@@ -23,3 +23,4 @@ ffmpeg_binaries_url=https://cdn.npmmirror.com/binaries/ffmpeg-static
 # 平铺依赖，以便electron-builder依赖分析与打包
 shamefully-hoist=true
 engine-strict = true
+update-notifier=false
--- a/electron/electron-env.d.ts
+++ b/electron/electron-env.d.ts
@@ -35,11 +35,11 @@ interface Window {
    ) => Promise<import('./types').ListFilesFromFolderRecord[]>
    edgeTtsGetVoiceList: () => Promise<import('./lib/edge-tts').EdgeTTSVoice[]>
    edgeTtsSynthesizeToBase64: (
-      params: import('./tts/types').edgeTtsSynthesizeCommonParams,
+      params: import('./tts/types').EdgeTtsSynthesizeCommonParams,
    ) => Promise<string>
    edgeTtsSynthesizeToFile: (
-      params: import('./tts/types').edgeTtsSynthesizeToFileParams,
-    ) => Promise<void>
+      params: import('./tts/types').EdgeTtsSynthesizeToFileParams,
+    ) => Promise<import('./tts/types').EdgeTtsSynthesizeToFileResult>
    renderVideo: (
      params: import('./ffmpeg/types').RenderVideoParams,
    ) => Promise<import('./ffmpeg/types').ExecuteFFmpegResult>
--- a/electron/preload.ts
+++ b/electron/preload.ts
@@ -7,7 +7,7 @@ import {
  BulkInsertOrUpdateParams,
 } from './sqlite/types'
 import { ListFilesFromFolderParams, SelectFolderParams } from './types'
-import { edgeTtsSynthesizeCommonParams } from './tts/types'
+import { EdgeTtsSynthesizeCommonParams } from './tts/types'
 import { RenderVideoParams } from './ffmpeg/types'

 // --------- 向界面渲染进程暴露某些API ---------
@@ -44,9 +44,9 @@ contextBridge.exposeInMainWorld('electron', {
  listFilesFromFolder: (params: ListFilesFromFolderParams) =>
    ipcRenderer.invoke('list-files-from-folder', params),
  edgeTtsGetVoiceList: () => ipcRenderer.invoke('edge-tts-get-voice-list'),
-  edgeTtsSynthesizeToBase64: (params: edgeTtsSynthesizeCommonParams) =>
+  edgeTtsSynthesizeToBase64: (params: EdgeTtsSynthesizeCommonParams) =>
    ipcRenderer.invoke('edge-tts-synthesize-to-base64', params),
-  edgeTtsSynthesizeToFile: (params: edgeTtsSynthesizeCommonParams) =>
+  edgeTtsSynthesizeToFile: (params: EdgeTtsSynthesizeCommonParams) =>
    ipcRenderer.invoke('edge-tts-synthesize-to-file', params),
  renderVideo: (params: RenderVideoParams) => ipcRenderer.invoke('render-video', params),
 })
--- a/electron/tts/index.ts
+++ b/electron/tts/index.ts
@@ -2,7 +2,12 @@ import fs from 'node:fs'
 import path from 'node:path'
 import { app } from 'electron'
 import { EdgeTTS } from '../lib/edge-tts'
-import { edgeTtsSynthesizeCommonParams, edgeTtsSynthesizeToFileParams } from './types'
+import { parseBuffer } from 'music-metadata'
+import {
+  EdgeTtsSynthesizeCommonParams,
+  EdgeTtsSynthesizeToFileParams,
+  EdgeTtsSynthesizeToFileResult,
+} from './types'

 const edgeTts = new EdgeTTS()

@@ -14,13 +19,15 @@ export function edgeTtsGetVoiceList() {
  return edgeTts.getVoices()
 }

-export async function edgeTtsSynthesizeToBase64(params: edgeTtsSynthesizeCommonParams) {
+export async function edgeTtsSynthesizeToBase64(params: EdgeTtsSynthesizeCommonParams) {
  const { text, voice, options } = params
  const result = await edgeTts.synthesize(text, voice, options)
  return result.toBase64()
 }

-export async function edgeTtsSynthesizeToFile(params: edgeTtsSynthesizeToFileParams) {
+export async function edgeTtsSynthesizeToFile(
+  params: EdgeTtsSynthesizeToFileParams,
+): Promise<EdgeTtsSynthesizeToFileResult> {
  const { text, voice, options, withCaption } = params
  const result = await edgeTts.synthesize(text, voice, options)

@@ -42,8 +49,8 @@ export async function edgeTtsSynthesizeToFile(params: edgeTtsSynthesizeToFilePar
    fs.writeFileSync(srtPath, srtString)
  }

-  // [TODO] 返回音频时长
+  const metadata = await parseBuffer(result.getBuffer())
  return {
-    duration: 0,
+    duration: metadata.format.duration,
  }
 }
--- a/electron/tts/types.ts
+++ b/electron/tts/types.ts
@@ -1,12 +1,19 @@
 import { SynthesisOptions } from '../lib/edge-tts'

-export interface edgeTtsSynthesizeCommonParams {
+export interface EdgeTtsSynthesizeCommonParams {
  text: string
  voice: string
  options: SynthesisOptions
 }

-export interface edgeTtsSynthesizeToFileParams extends edgeTtsSynthesizeCommonParams {
+export interface EdgeTtsSynthesizeToFileParams extends EdgeTtsSynthesizeCommonParams {
  withCaption?: boolean
  outputPath?: string
 }
+
+export interface EdgeTtsSynthesizeToFileResult {
+  /**
+   * 合成后的音频时长，单位秒
+   */
+  duration: number | undefined
+}
--- a/package.json
+++ b/package.json
@@ -20,6 +20,7 @@
    "axios": "^1.11.0",
    "better-sqlite3": "9.6.0",
    "ffmpeg-static": "^5.2.0",
+    "music-metadata": "^11.7.3",
    "subtitle": "4.2.2-alpha.0",
    "ws": "^8.18.3"
  },
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -17,6 +17,9 @@ importers:
      ffmpeg-static:
        specifier: ^5.2.0
        version: 5.2.0
+      music-metadata:
+        specifier: ^11.7.3
+        version: 11.7.3
      subtitle:
        specifier: 4.2.2-alpha.0
        version: 4.2.2-alpha.0
@@ -765,6 +768,13 @@ packages:
    resolution: {integrity: sha512-4BAffykYOgO+5nzBWYwE3W90sBgLJoUPRWWcL8wlyiM8IB8ipJz3UMJ9KXQd1RKQXpKp8Tutn80HZtWsu2u76w==}
    engines: {node: '>=10'}

+  '@tokenizer/inflate@0.2.7':
+    resolution: {integrity: sha512-MADQgmZT1eKjp06jpI2yozxaU9uVs4GzzgSL+uEq7bVcJ9V1ZXQkeGNql1fsSI0gMy1vhvNTNbUqrx+pZfJVmg==}
+    engines: {node: '>=18'}
+
+  '@tokenizer/token@0.3.0':
+    resolution: {integrity: sha512-OvjF+z51L3ov0OyAU0duzsYuvO01PH7x4t6DJx+guahgTnBHkhJdG7soQeTSFLWN3efnHyibZ4Z8l2EuWwJN3A==}
+
  '@tootallnate/once@2.0.0':
    resolution: {integrity: sha512-XCuKFP5PS55gnMVu3dty8KPatLqUoy/ZYzDzAGCQ8JNFCkLXzmI7vNHCR+XpbZaMWQK/vQubr7PkYq8g470J/A==}
    engines: {node: '>= 10'}
@@ -1315,6 +1325,10 @@ packages:
    resolution: {integrity: sha512-5IKcdX0nnYavi6G7TtOhwkYzyjfJlatbjMjuLSfE2kYT5pMDOilZ4OvMhi637CcDICTmz3wARPoyhqyX1Y+XvA==}
    engines: {node: ^14.18.0 || >=16.10.0}

+  content-type@1.0.5:
+    resolution: {integrity: sha512-nTjqfcBFEipKdXCv4YDQWCfmcLZKm81ldF0pAopTvyrFGVbcR6P/VAAd5G7N+0tTr8QqiU0tFadD6FK4NtJwOA==}
+    engines: {node: '>= 0.6'}
+
  convert-source-map@2.0.0:
    resolution: {integrity: sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg==}

@@ -1591,6 +1605,9 @@ packages:
      picomatch:
        optional: true

+  fflate@0.8.2:
+    resolution: {integrity: sha512-cPJU47OaAoCbg0pBvzsgpTPhmhqI5eJjh/JIu8tPj5q+T7iLvW/JAYUqmE7KOB4R1ZyEhzBaIQpQpardBF5z8A==}
+
  ffmpeg-static@5.2.0:
    resolution: {integrity: sha512-WrM7kLW+do9HLr+H6tk7LzQ7kPqbAgLjdzNE32+u3Ff11gXt9Kkkd2nusGFrlWMIe+XaA97t+I8JS7sZIrvRgA==}
    engines: {node: '>=16'}
@@ -1599,6 +1616,10 @@ packages:
    resolution: {integrity: sha512-d+l3qxjSesT4V7v2fh+QnmFnUWv9lSpjarhShNTgBOfA0ttejbQUAlHLitbjkoRiDulW0OPoQPYIGhIC8ohejg==}
    engines: {node: '>=18'}

+  file-type@21.0.0:
+    resolution: {integrity: sha512-ek5xNX2YBYlXhiUXui3D/BXa3LdqPmoLJ7rqEx2bKJ7EAUEfmXgW0Das7Dc6Nr9MvqaOnIqiPV0mZk/r/UpNAg==}
+    engines: {node: '>=20'}
+
  file-uri-to-path@1.0.0:
    resolution: {integrity: sha512-0Zt+s3L7Vf1biwWZ29aARiVYLx7iMGnEUl9x33fbB/j3jR81u/O2LbqK+Bm1CDSNDKVtJ/YjwY7TUd5SkeLQLw==}

@@ -1990,6 +2011,10 @@ packages:
  mdn-data@2.12.2:
    resolution: {integrity: sha512-IEn+pegP1aManZuckezWCO+XZQDplx1366JoVhTpMpBB1sPey/SbveZQUosKiKiGYjg1wH4pMlNgXbCiYgihQA==}

+  media-typer@1.1.0:
+    resolution: {integrity: sha512-aisnrDP4GNe06UcKFnV5bfMNPBUw4jsLGaWwWfnH3v02GnBuXX2MCVn5RbrWo0j3pczUilYblq7fQ7Nw2t5XKw==}
+    engines: {node: '>= 0.8'}
+
  micromatch@4.0.8:
    resolution: {integrity: sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==}
    engines: {node: '>=8.6'}
@@ -2076,6 +2101,10 @@ packages:
  multipipe@4.0.0:
    resolution: {integrity: sha512-jzcEAzFXoWwWwUbvHCNPwBlTz3WCWe/jPcXSmTfbo/VjRwRTfvLZ/bdvtiTdqCe8d4otCSsPCbhGYcX+eggpKQ==}

+  music-metadata@11.7.3:
+    resolution: {integrity: sha512-xYbaSFpHi6qOUTFCb7fvC4/6Uk1NAJey2pSwNQPqJkCLwleYGUWVRKlxnNy2MsTaDRPnIwXdkgrmeiP/GDq/ww==}
+    engines: {node: '>=18'}
+
  nanoid@3.3.11:
    resolution: {integrity: sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w==}
    engines: {node: ^10 || ^12 || ^13.7 || ^14 || >=15.0.1}
@@ -2474,6 +2503,10 @@ packages:
    resolution: {integrity: sha512-4gB8na07fecVVkOI6Rs4e7T6NOTki5EmL7TUduTs6bu3EdnSycntVJ4re8kgZA+wx9IueI2Y11bfbgwtzuE0KQ==}
    engines: {node: '>=0.10.0'}

+  strtok3@10.3.4:
+    resolution: {integrity: sha512-KIy5nylvC5le1OdaaoCJ07L+8iQzJHGH6pWDuzS+d07Cu7n1MZ2x26P8ZKIWfbK02+XIL8Mp4RkWeqdUCrDMfg==}
+    engines: {node: '>=18'}
+
  subtitle@4.2.2-alpha.0:
    resolution: {integrity: sha512-IMS+L8lXjOLveg5BC/bVZy+36/x2NqMIQmVDhbquDpxLnXugzmz7/yHHFZ7b9YLfqNaBdXwh1lsnAds3g1FnCQ==}
    engines: {node: '>=10'}
@@ -2531,6 +2564,10 @@ packages:
    resolution: {integrity: sha512-65P7iz6X5yEr1cwcgvQxbbIw7Uk3gOy5dIdtZ4rDveLqhrdJP+Li/Hx6tyK0NEb+2GCyneCMJiGqrADCSNk8sQ==}
    engines: {node: '>=8.0'}

+  token-types@6.0.4:
+    resolution: {integrity: sha512-MD9MjpVNhVyH4fyd5rKphjvt/1qj+PtQUz65aFqAZA6XniWAuSFRjLk3e2VALEFlh9OwBpXUN7rfeqSnT/Fmkw==}
+    engines: {node: '>=14.16'}
+
  totalist@3.0.1:
    resolution: {integrity: sha512-sf4i37nQ2LBx4m3wB74y+ubopq6W/dIzXg0FDGjsYnZHVa1Da8FH853wlL2gtUhg+xJXjfk3kUZS3BRoQeoQBQ==}
    engines: {node: '>=6'}
@@ -2556,6 +2593,10 @@ packages:
  ufo@1.6.1:
    resolution: {integrity: sha512-9a4/uxlTWJ4+a5i0ooc1rU7C7YOw3wT+UGqdeNNHWnOF9qcMBgLRS+4IYUqbczewFx4mLEig6gawh7X6mFlEkA==}

+  uint8array-extras@1.4.0:
+    resolution: {integrity: sha512-ZPtzy0hu4cZjv3z5NW9gfKnNLjoz4y6uv4HlelAjDK7sY/xOkKZv9xK/WQpcsBB3jEybChz9DPC2U/+cusjJVQ==}
+    engines: {node: '>=18'}
+
  unconfig@7.3.2:
    resolution: {integrity: sha512-nqG5NNL2wFVGZ0NA/aCFw0oJ2pxSf1lwg4Z5ill8wd7K4KX/rQbHlwbh+bjctXL5Ly1xtzHenHGOK0b+lG6JVg==}

@@ -3407,6 +3448,16 @@ snapshots:
    dependencies:
      defer-to-connect: 2.0.1

+  '@tokenizer/inflate@0.2.7':
+    dependencies:
+      debug: 4.4.1
+      fflate: 0.8.2
+      token-types: 6.0.4
+    transitivePeerDependencies:
+      - supports-color
+
+  '@tokenizer/token@0.3.0': {}
+
  '@tootallnate/once@2.0.0': {}

  '@types/better-sqlite3@7.6.13':
@@ -4166,6 +4217,8 @@ snapshots:

  consola@3.4.2: {}

+  content-type@1.0.5: {}
+
  convert-source-map@2.0.0: {}

  copy-anything@3.0.5:
@@ -4483,6 +4536,8 @@ snapshots:
    optionalDependencies:
      picomatch: 4.0.2

+  fflate@0.8.2: {}
+
  ffmpeg-static@5.2.0:
    dependencies:
      '@derhuerst/http-basic': 8.2.4
@@ -4496,6 +4551,15 @@ snapshots:
    dependencies:
      is-unicode-supported: 2.1.0

+  file-type@21.0.0:
+    dependencies:
+      '@tokenizer/inflate': 0.2.7
+      strtok3: 10.3.4
+      token-types: 6.0.4
+      uint8array-extras: 1.4.0
+    transitivePeerDependencies:
+      - supports-color
+
  file-uri-to-path@1.0.0: {}

  filelist@1.0.4:
@@ -4887,6 +4951,8 @@ snapshots:

  mdn-data@2.12.2: {}

+  media-typer@1.1.0: {}
+
  micromatch@4.0.8:
    dependencies:
      braces: 3.0.3
@@ -4960,6 +5026,19 @@ snapshots:
      duplexer2: 0.1.4
      object-assign: 4.1.1

+  music-metadata@11.7.3:
+    dependencies:
+      '@tokenizer/token': 0.3.0
+      content-type: 1.0.5
+      debug: 4.4.1
+      file-type: 21.0.0
+      media-typer: 1.1.0
+      strtok3: 10.3.4
+      token-types: 6.0.4
+      uint8array-extras: 1.4.0
+    transitivePeerDependencies:
+      - supports-color
+
  nanoid@3.3.11: {}

  nanoid@5.1.5: {}
@@ -5359,6 +5438,10 @@ snapshots:

  strip-json-comments@2.0.1: {}

+  strtok3@10.3.4:
+    dependencies:
+      '@tokenizer/token': 0.3.0
+
  subtitle@4.2.2-alpha.0:
    dependencies:
      '@types/multipipe': 3.0.5
@@ -5436,6 +5519,11 @@ snapshots:
    dependencies:
      is-number: 7.0.0

+  token-types@6.0.4:
+    dependencies:
+      '@tokenizer/token': 0.3.0
+      ieee754: 1.2.1
+
  totalist@3.0.1: {}

  truncate-utf8-bytes@1.0.2:
@@ -5455,6 +5543,8 @@ snapshots:

  ufo@1.6.1: {}

+  uint8array-extras@1.4.0: {}
+
  unconfig@7.3.2:
    dependencies:
      '@quansync/fs': 0.1.3
--- a/src/views/Home/components/tts-control.vue
+++ b/src/views/Home/components/tts-control.vue
@@ -129,7 +129,7 @@ const synthesizedSpeechToFile = async (option?: { withCaption?: boolean }) => {
  if (!configValid()) throw new Error('TTS语音合成配置无效')

  try {
-    await window.electron.edgeTtsSynthesizeToFile({
+    const result = await window.electron.edgeTtsSynthesizeToFile({
      text: appStore.tryListeningText,
      voice: appStore.voice!.ShortName,
      options: {
@@ -137,6 +137,7 @@ const synthesizedSpeechToFile = async (option?: { withCaption?: boolean }) => {
      },
      withCaption: option?.withCaption,
    })
+    return result
  } catch (error) {
    console.log('语音合成失败', error)
    toast.error('语音合成失败，请检查网络')
--- a/src/views/Home/components/video-manage.vue
+++ b/src/views/Home/components/video-manage.vue
@@ -102,7 +102,9 @@ const refreshAssets = async () => {
 refreshAssets()

 // 获取视频分镜随机素材片段
-const getVideoSegments = async () => {}
+const getVideoSegments = async (options: { duration: number }) => {
+  
+}

 defineExpose({ getVideoSegments })
 </script>
--- a/src/views/Home/components/video-render.vue
+++ b/src/views/Home/components/video-render.vue
@@ -18,7 +18,7 @@
            size="x-large"
            color="deep-purple-accent-3"
            prepend-icon="mdi-rocket-launch"
-            @click="onRenderVideo"
+            @click="emit('renderVideo')"
          >
            开始合成
          </v-btn>
@@ -104,8 +104,8 @@ import { useAppStore } from '@/store'

 const appStore = useAppStore()

-defineEmits<{
-  renderVideo(): void
+const emit = defineEmits<{
+  (e: 'renderVideo'): void
 }>()

 // 配置合成选项
--- a/src/views/Home/index.vue
+++ b/src/views/Home/index.vue
@@ -49,14 +49,21 @@ const handleRenderVideo = async () => {
      return
    }

-    toast.info('即将开发完成，敬请期待')
-    return
-
    // TTS合成语音
-    await TtsControlInstance.value?.synthesizedSpeechToFile({ withCaption: true })
+    const ttsResult = await TtsControlInstance.value?.synthesizedSpeechToFile({ withCaption: true })
+    if (ttsResult?.duration === undefined) {
+      toast.warning('语音合成失败，音频文件损坏')
+      return
+    }
+    if (ttsResult?.duration === 0) {
+      toast.warning('语音时长为0秒，可能文案为空')
+      return
+    }

    // 获取视频片段
-    // const videoSegments = VideoManageInstance.value?.getVideoSegments()
+    const videoSegments = VideoManageInstance.value?.getVideoSegments({
+      duration: ttsResult.duration,
+    })

    // await window.electron.renderVideo({})
  } catch (error) {