Merge pull request #33 from Lazy-CZ/fix/export-audio-fix

fix: 修复批量导出 wav 音频语速变快、音调升高（采样率不匹配）问题

src/main/export-service.ts

@@ -941,10 +941,7 @@ async function runSingleExport(
       request.format === 'html'
         ? options.outputFolderName || safeFilePart(request.outputName)
         : `${safeFilePart(request.outputName)}_${exportStamp()}`
-    const root =
-      options.outputRoot ||
-      request.outputDirectory ||
-      (await resolveDefaultExportRoot(outputFolder))
+    const root = options.outputRoot || request.outputDirectory || (await resolveDefaultExportRoot(outputFolder))
     await fs.mkdir(root, { recursive: true })
     const outputDir = join(root, outputFolder)
     const outputPath =
@@ -1236,7 +1233,16 @@ async function runSingleExport(
                 markResourceExists(voiceUrl)
               }
               message.voiceDataUrl = voiceUrl
-              message.voiceDuration = Math.max(1, Math.round(audioBuffer.length / (24000 * 2)))
+              // 读取 WAV 头中的采样率，避免按错误采样率计算时长（Silk 解码为 16kHz）
+              const wavSampleRate =
+                audioBuffer.length >= 44 ? audioBuffer.readUInt32LE(24) : 16000
+              const wavChannels =
+                audioBuffer.length >= 44 ? audioBuffer.readUInt16LE(22) : 1
+              const pcmBytes = Math.max(0, audioBuffer.length - 44)
+              message.voiceDuration = Math.max(
+                1,
+                Math.round(pcmBytes / (wavSampleRate * wavChannels * 2))
+              )
             } catch (error) {
               keepMediaError(
                 request,
@@ -1478,10 +1484,13 @@ async function runSingleExport(
         } else if (message.contentData.type === 'sticker' && stickerService) {
           const stickerSource = message.contentData.url || message.contentData.thumbUrl
           const result = await stickerService.resolveSticker(stickerSource, message.contentData.md5)
-          const decoded = result.data ? decodeDataUrl(result.data) : null
-          const stickerExtension = decoded ? detectAssetExtension(decoded.buffer) : null
-          if (decoded && stickerExtension) {
-            const name = `sticker_${bufferHashPart(decoded.buffer)}.${stickerExtension}`
+          const decoded = result.data
+            ? decodeDataUrl(result.data)
+            : stickerSource
+              ? await readAvatarAsset(stickerSource)
+              : null
+          if (decoded) {
+            const name = `sticker_${bufferHashPart(decoded.buffer)}.${decoded.extension}`
             const mediaUrl = `media/${name}`
             if (!(await resourceExists(mediaUrl))) {
               await fs.writeFile(join(outputDir, 'media', name), decoded.buffer)

src/main/voice-service.ts

@@ -125,7 +125,11 @@ export class VoiceService {
           codec: 'silk',
           sourceHash: createHash('sha256').update(silkData).digest('hex')
         })
-        const wavData = this.createWavBuffer(decoded.pcm, 24000)
+        const wavData = this.createWavBuffer(
+          decoded.pcm,
+          decoded.sampleRate,
+          decoded.channels
+        )
         const data = wavData.toString('base64')
         const cacheKey = this.buildCacheKey(
           reference.sessionId,
@@ -239,7 +243,7 @@ export class VoiceService {
 
   private createWavBuffer(
     pcmData: Buffer,
-    sampleRate: number = 24000,
+    sampleRate: number = 16000,
     channels: number = 1
   ): Buffer {
     const pcmLength = pcmData.length

tests/unit/voice-service.test.ts

@@ -2,6 +2,29 @@ import { describe, expect, it, vi } from 'vitest'
 import { VoiceService } from '../../src/main/voice-service'
 
 describe('VoiceService batch lookup', () => {
+  it('writes the decoded sample rate and duration into batch WAV output', async () => {
+    const getVoiceDataBatch = vi.fn().mockResolvedValue([{ success: true, hex: '0102' }])
+    const service = new VoiceService({ getVoiceDataBatch } as never)
+    const decoder = (service as unknown as {
+      decoderRegistry: { decode: ReturnType<typeof vi.fn> }
+    }).decoderRegistry
+    vi.spyOn(decoder, 'decode').mockResolvedValue({
+      pcm: Buffer.alloc(16_000 * 2),
+      sampleRate: 16_000,
+      channels: 1
+    })
+
+    const [result] = await service.resolveVoices([
+      { sessionId: 'session', localId: 10, createTime: 100, svrId: '1000' }
+    ])
+
+    expect(result.success).toBe(true)
+    const wav = Buffer.from(result.data!, 'base64')
+    expect(wav.readUInt32LE(24)).toBe(16_000)
+    expect(wav.readUInt16LE(22)).toBe(1)
+    expect((wav.length - 44) / (wav.readUInt32LE(24) * wav.readUInt16LE(22) * 2)).toBe(1)
+  })
+
   it('retries failed batch entries with the compatible single-item lookup', async () => {
     const getVoiceDataBatch = vi.fn().mockResolvedValue([
       { success: false, error: '获取语音数据失败' },