azure tts使用go sdk在流中生成wav少46字节

Question

我使用这个示例https://github.com/Microsoft/cognitive-services-speech-sdk-go/blob/1af83b0cf8fb/samples/synthesizer/to_audio_data_stream.go

我将字节写入文件，但发现文件无法打开

stream.SaveToWavFileAsync("fun.wav")
//use this func can save a file which can open

输出

Synthesis started.
Synthesizing, audio chunk size 65582.
Synthesizing, audio chunk size 294510.
Synthesizing, audio chunk size 56446.
Synthesizing, audio chunk size 65582.
Synthesizing, audio chunk size 1710.
Synthesized, audio length 483646.
Read [483600] bytes from audio data stream.

流少46字节

Answer 1

pcm需要添加wav头。

func PcmToWav(dst []byte, numChannel int, sampleRate int) (resDst []byte) {
    byteDst := dst
    longSampleRate := sampleRate
    byteRate := 16 * sampleRate * numChannel / 8
    totalAudioLen := len(byteDst)
    totalDataLen := totalAudioLen + 36
    var header = make([]byte, 44)
    // RIFF/WAVE header
    header[0] = 'R'
    header[1] = 'I'
    header[2] = 'F'
    header[3] = 'F'
    header[4] = byte(totalDataLen & 0xff)
    header[5] = byte((totalDataLen >> 8) & 0xff)
    header[6] = byte((totalDataLen >> 16) & 0xff)
    header[7] = byte((totalDataLen >> 24) & 0xff)
    //WAVE
    header[8] = 'W'
    header[9] = 'A'
    header[10] = 'V'
    header[11] = 'E'
    // 'fmt ' chunk
    header[12] = 'f'
    header[13] = 'm'
    header[14] = 't'
    header[15] = ' '
    // 4 bytes: size of 'fmt ' chunk
    header[16] = 16
    header[17] = 0
    header[18] = 0
    header[19] = 0
    // format = 1
    header[20] = 1
    header[21] = 0
    header[22] = byte(numChannel)
    header[23] = 0
    header[24] = byte(longSampleRate & 0xff)
    header[25] = byte((longSampleRate >> 8) & 0xff)
    header[26] = byte((longSampleRate >> 16) & 0xff)
    header[27] = byte((longSampleRate >> 24) & 0xff)
    header[28] = byte(byteRate & 0xff)
    header[29] = byte((byteRate >> 8) & 0xff)
    header[30] = byte((byteRate >> 16) & 0xff)
    header[31] = byte((byteRate >> 24) & 0xff)
    // block align
    header[32] = byte(2 * 16 / 8)
    header[33] = 0
    // bits per sample
    header[34] = 16
    header[35] = 0
    //data
    header[36] = 'd'
    header[37] = 'a'
    header[38] = 't'
    header[39] = 'a'
    header[40] = byte(totalAudioLen & 0xff)
    header[41] = byte((totalAudioLen >> 8) & 0xff)
    header[42] = byte((totalAudioLen >> 16) & 0xff)
    header[43] = byte((totalAudioLen >> 24) & 0xff)

    resDst = append(header, dst...)
    return
}