azure tts use go sdk generate in stream to wav less 46 byte

Question

i use this samplehttps://github.com/Microsoft/cognitive-services-speech-sdk-go/blob/1af83b0cf8fb/samples/synthesizer/to_audio_data_stream.go

and i wirte byte to file and i find file cant open

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

output

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.

the stream less 46 bytes

Answer 1

pcm need add wav head.

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
}