我正在尝试对从WebRTC呼叫中保存的PCM格式的音频文件进行转码。 WebRTC报告的音频流格式为16位深度,1个通道和48000 Hz采样率。我想将音频转换为MP3,以便以后可以将音频作为背景音轨添加到Unity UWP应用的屏幕录像中(使用MediaComposition)。我在第一部分遇到麻烦:尝试将PCM音频文件转码为MP3文件。当我尝试准备转码时,preparedTranscodeResult.CanTranscode
返回false
。以下是我的代码。
StorageFile remoteAudioPCMFile = await StorageFile.GetFileFromPathAsync(Path.Combine(Application.temporaryCachePath, "remote.pcm").Replace("/", "\\"));
StorageFolder tempFolder = await StorageFolder.GetFolderFromPathAsync(Application.temporaryCachePath.Replace("/", "\\"));
StorageFile remoteAudioMP3File = await tempFolder.CreateFileAsync("remote.mp3", CreationCollisionOption.ReplaceExisting);
MediaEncodingProfile profile = MediaEncodingProfile.CreateMp3(AudioEncodingQuality.Auto);
profile.Audio.BitsPerSample = 16;
profile.Audio.ChannelCount = 1;
profile.Audio.SampleRate = 48000;
MediaTranscoder transcoder = new MediaTranscoder();
var preparedTranscodeResult = await transcoder.PrepareFileTranscodeAsync(remoteAudioPCMFile, remoteAudioMP3File, profile);
if (preparedTranscodeResult.CanTranscode)
{
await preparedTranscodeResult.TranscodeAsync();
}
else
{
if (remoteAudioPCMFile != null)
{
await remoteAudioPCMFile.DeleteAsync();
}
if (remoteAudioMP3File != null)
{
await remoteAudioMP3File.DeleteAsync();
}
switch (preparedTranscodeResult.FailureReason)
{
case TranscodeFailureReason.CodecNotFound:
Debug.LogError("Codec not found.");
break;
case TranscodeFailureReason.InvalidProfile:
Debug.LogError("Invalid profile.");
break;
default:
Debug.LogError("Unknown failure.");
break;
}
}
所以我要做的是在开始将数据写入流之前,将标头写入FileStream
。我是从this post获得的。
private void WriteWavHeader(FileStream stream, bool isFloatingPoint, ushort channelCount, ushort bitDepth, int sampleRate, int totalSampleCount)
{
stream.Position = 0;
// RIFF header.
// Chunk ID.
stream.Write(Encoding.ASCII.GetBytes("RIFF"), 0, 4);
// Chunk size.
stream.Write(BitConverter.GetBytes((bitDepth / 8 * totalSampleCount) + 36), 0, 4);
// Format.
stream.Write(Encoding.ASCII.GetBytes("WAVE"), 0, 4);
// Sub-chunk 1.
// Sub-chunk 1 ID.
stream.Write(Encoding.ASCII.GetBytes("fmt "), 0, 4);
// Sub-chunk 1 size.
stream.Write(BitConverter.GetBytes(16), 0, 4);
// Audio format (floating point (3) or PCM (1)). Any other format indicates compression.
stream.Write(BitConverter.GetBytes((ushort)(isFloatingPoint ? 3 : 1)), 0, 2);
// Channels.
stream.Write(BitConverter.GetBytes(channelCount), 0, 2);
// Sample rate.
stream.Write(BitConverter.GetBytes(sampleRate), 0, 4);
// Bytes rate.
stream.Write(BitConverter.GetBytes(sampleRate * channelCount * (bitDepth / 8)), 0, 4);
// Block align.
stream.Write(BitConverter.GetBytes(channelCount * (bitDepth / 8)), 0, 2);
// Bits per sample.
stream.Write(BitConverter.GetBytes(bitDepth), 0, 2);
// Sub-chunk 2.
// Sub-chunk 2 ID.
stream.Write(Encoding.ASCII.GetBytes("data"), 0, 4);
// Sub-chunk 2 size.
stream.Write(BitConverter.GetBytes(bitDepth / 8 * totalSampleCount), 0, 4);
}