使用 Swift 在 iOS 中将音频 mp3 文件转换为具有以下特征的音频类型 raw 的最有效方法是什么?
single-channel (monaural)
little-endian
unheadered
16-bit signed
PCM
sampled at 16000 Hz
使用 Swift 在 iOS 中将音频 mp3 文件转换为具有以下特征的音频类型 raw 的最有效方法是什么?
single-channel (monaural)
little-endian
unheadered
16-bit signed
PCM
sampled at 16000 Hz
我不知道这会有所帮助,或者这就是你所追求的。
有一个与此问题相关的解决方案,与您在此处之后的内容有关
我修改了你之后的答案,我不是这方面的专家,但我会尽力而为
import AVFoundation
public final class AVAudioFileConverter {
var rwAudioSerializationQueue: DispatchQueue!
var asset:AVAsset!
var assetReader:AVAssetReader!
var assetReaderAudioOutput:AVAssetReaderTrackOutput!
var assetWriter:AVAssetWriter!
var assetWriterAudioInput:AVAssetWriterInput!
var outputURL:URL
var inputURL:URL
public init?(inputFileURL: URL, outputFileURL: URL) {
inputURL = inputFileURL
outputURL = outputFileURL
if (FileManager.default.fileExists(atPath: inputURL.absoluteString)) {
print("Input file does not exist at file path \(inputURL.absoluteString)")
return nil
}
}
public func convert() {
let rwAudioSerializationQueueDescription = " rw audio serialization queue"
// Create the serialization queue to use for reading and writing the audio data.
rwAudioSerializationQueue = DispatchQueue(label: rwAudioSerializationQueueDescription)
assert(rwAudioSerializationQueue != nil, "Failed to initialize Dispatch Queue")
asset = AVAsset(url: inputURL)
assert(asset != nil, "Error creating AVAsset from input URL")
print("Output file path -> ", outputURL.absoluteString)
asset.loadValuesAsynchronously(forKeys: ["tracks"], completionHandler: {
var success = true
var localError:NSError?
success = (self.asset.statusOfValue(forKey: "tracks", error: &localError) == AVKeyValueStatus.loaded)
// Check for success of loading the assets tracks.
if (success) {
// If the tracks loaded successfully, make sure that no file exists at the output path for the asset writer.
let fm = FileManager.default
let localOutputPath = self.outputURL.path
if (fm.fileExists(atPath: localOutputPath)) {
do {
try fm.removeItem(atPath: localOutputPath)
success = true
} catch {
print("Error trying to remove output file at path -> \(localOutputPath)")
}
}
}
if (success) {
success = self.setupAssetReaderAndAssetWriter()
} else {
print("Failed setting up Asset Reader and Writer")
}
if (success) {
success = self.startAssetReaderAndWriter()
return
} else {
print("Failed to start Asset Reader and Writer")
}
})
}
func setupAssetReaderAndAssetWriter() -> Bool {
do {
assetReader = try AVAssetReader(asset: asset)
} catch {
print("Error Creating AVAssetReader")
}
do {
assetWriter = try AVAssetWriter(outputURL: outputURL, fileType: AVFileType.wav)
} catch {
print("Error Creating AVAssetWriter")
}
var assetAudioTrack:AVAssetTrack? = nil
let audioTracks = asset.tracks(withMediaType: AVMediaType.audio)
if (audioTracks.count > 0) {
assetAudioTrack = audioTracks[0]
}
if (assetAudioTrack != nil) {
let decompressionAudioSettings:[String : Any] = [
AVFormatIDKey:Int(kAudioFormatLinearPCM)
]
assetReaderAudioOutput = AVAssetReaderTrackOutput(track: assetAudioTrack!, outputSettings: decompressionAudioSettings)
assert(assetReaderAudioOutput != nil, "Failed to initialize AVAssetReaderTrackOutout")
assetReader.add(assetReaderAudioOutput)
var channelLayout = AudioChannelLayout()
memset(&channelLayout, 0, MemoryLayout<AudioChannelLayout>.size);
channelLayout.mChannelLayoutTag = kAudioChannelLayoutTag_Stereo;
let outputSettings:[String : Any] = [
AVFormatIDKey: Int(kAudioFormatLinearPCM),
AVSampleRateKey: 44100,
AVNumberOfChannelsKey: 2,
AVChannelLayoutKey: NSData(bytes:&channelLayout, length: MemoryLayout.size(ofValue: AudioChannelLayout.self)),
AVLinearPCMBitDepthKey: 16,
AVLinearPCMIsNonInterleaved: false,
AVLinearPCMIsFloatKey: false,
AVLinearPCMIsBigEndianKey: false,
]
assetWriterAudioInput = AVAssetWriterInput(mediaType: AVMediaType.audio, outputSettings: outputSettings)
assert(rwAudioSerializationQueue != nil, "Failed to initialize AVAssetWriterInput")
assetWriter.add(assetWriterAudioInput)
}
print("Finsihed Setup of AVAssetReader and AVAssetWriter")
return true
}
func startAssetReaderAndWriter() -> Bool {
print("STARTING ASSET WRITER")
assetWriter.startWriting()
assetReader.startReading()
assetWriter.startSession(atSourceTime: CMTime.zero)
assetWriterAudioInput.requestMediaDataWhenReady(on: rwAudioSerializationQueue, using: {
while(self.assetWriterAudioInput.isReadyForMoreMediaData ) {
var sampleBuffer = self.assetReaderAudioOutput.copyNextSampleBuffer()
if(sampleBuffer != nil) {
self.assetWriterAudioInput.append(sampleBuffer!)
sampleBuffer = nil
} else {
self.assetWriterAudioInput.markAsFinished()
self.assetReader.cancelReading()
self.assetWriter.finishWriting {
print("Asset Writer Finished Writing")
}
break
}
}
})
return true
}
}
用法
let inputFilePath = URL(fileURLWithPath: "/path/to/file.mp3")
let outputFileURL = URL(fileURLWithPath: "/path/to/output/output.wav")
if let audioConverter = AVAudioFileConverter(inputFileURL: inputFilePath,
outputFileURL: outputFileURL) {
audioConverter.convert()
}
输入文件信息
File: /path/12.mp3
File type ID: MPG3
Num Tracks: 1
----
Data format: 2 ch, 44100 Hz, '.mp3' (0x00000000) 0 bits/channel, 0 bytes/packet, 1152 frames/packet, 0 bytes/frame
no channel layout.
estimated duration: 1.149375 sec
audio bytes: 18390
audio packets: 44
bit rate: 128000 bits per second
packet size upper bound: 1052
maximum packet size: 418
audio data file offset: 417
optimized
audio 48510 valid frames + 576 priming + 1602 remainder = 50688
输出文件信息
File type ID: WAVE
Num Tracks: 1
----
Data format: 2 ch, 44100 Hz, 'lpcm' (0x0000000C) 16-bit little-endian signed integer
no channel layout.
estimated duration: 1.136327 sec
audio bytes: 200448
audio packets: 50112
bit rate: 1411200 bits per second
packet size upper bound: 4
maximum packet size: 4
audio data file offset: 4096
optimized
source bit depth: I16
File Name: output.wav
File Size: 200 kB
File Type: WAV
File Type Extension: wav
MimeType: audio/x-wav
Encoding: Microsoft PCM
Num Channels: 2
Sample Rate: 44100
Avg Bytes Per Sec: 176400
Bits Per Sample: 16
Duration: 1.16 s
Category: audio
如果要更改设置,只需更改 outputSettings 这部分
let outputSettings:[String : Any] = [
AVFormatIDKey: Int(kAudioFormatLinearPCM),
AVSampleRateKey: 44100,
AVNumberOfChannelsKey: 2,
AVChannelLayoutKey: NSData(bytes:&channelLayout, length: MemoryLayout.size(ofValue: AudioChannelLayout.self)),
AVLinearPCMBitDepthKey: 16,
AVLinearPCMIsNonInterleaved: false,
AVLinearPCMIsFloatKey: false,
AVLinearPCMIsBigEndianKey: false,
]
我希望这将有所帮助。