音频aac硬编码

一、前言

上一篇文章，分享了视频h264硬编码，有了视频，怎么能少了音频呢！接下来分享音频aac硬编码。

二、音频硬编码

1.编码器类DDHardwareAudioEncoder.h文件中，该类继承自DDAudioEncoding（编码器抽象接口类）其中，DDLiveAudioConfiguration是音频配置文件，里面是音频采样率、码率、声道数目等音频相关属性，具体文件实现如下：

#import "DDAudioEncoding.h"

@interface DDHardwareAudioEncoder : NSObject

#pragma mark - Initializer
///=============================================================================
/// @name Initializer
///=============================================================================
- (nullable instancetype)init UNAVAILABLE_ATTRIBUTE;
+ (nullable instancetype)new UNAVAILABLE_ATTRIBUTE;

@end

2.编码器抽象接口类DDAudioEncoding.h文件实现如下：
其中DDAudioFrame类是编码成功后数据处理类，里面有每帧编码成功后的data、nSamplePerSec（采样率）、nChannel（通道数）、audioHeader（音频头）等属性。

#import 
#import 
#import "DDAudioFrame.h"
#import "DDLiveAudioConfiguration.h"

@protocol DDAudioEncoding;
/// 编码器编码后回调
@protocol DDAudioEncodingDelegate 
@required
- (void)audioEncoder:(nullable id)encoder audioFrame:(nullable DDAudioFrame*)frame;
@end

/// 编码器抽象的接口
@protocol DDAudioEncoding 
@required
- (void)encodeAudioData:(AudioBufferList)inBufferList timeStamp:(uint64_t)timeStamp;

@optional
- (nullable instancetype)initWithAudioStreamConfiguration:(nullable DDLiveAudioConfiguration*)configuration;
- (void)setDelegate:(nullable id)delegate;
- (nullable NSData*)adtsData:(NSInteger)channel rawDataLength:(NSInteger)rawDataLength;

@end

3.下面是具体实现的DDHardwareAudioEncoder.m类文件

#import "DDHardwareAudioEncoder.h"

@interface DDHardwareAudioEncoder (){
    AudioConverterRef m_converter;
    char *aacBuf;
}
@property (nonatomic, strong) DDLiveAudioConfiguration *configuration;
@property (nonatomic, weak) id aacDeleage;

@end

@implementation DDHardwareAudioEncoder

- (instancetype)initWithAudioStreamConfiguration:(DDLiveAudioConfiguration *)configuration{
    if(self = [super init]){
        _configuration = configuration;
    }
    return self;
}

- (void)dealloc{
    if(aacBuf) free(aacBuf);
}

#pragma mark -- DDAudioEncoder
- (void)setDelegate:(id)delegate{
    _aacDeleage = delegate;
}

- (void)encodeAudioData:(AudioBufferList)inBufferList timeStamp:(uint64_t)timeStamp{
    if (![self createAudioConvert]){
        return;
    }
    
    if(!aacBuf){
        aacBuf = malloc(inBufferList.mBuffers[0].mDataByteSize);
    }
    
    // 初始化一个输出缓冲列表
    AudioBufferList outBufferList;
    outBufferList.mNumberBuffers              = 1;
    outBufferList.mBuffers[0].mNumberChannels = inBufferList.mBuffers[0].mNumberChannels;
    outBufferList.mBuffers[0].mDataByteSize   = inBufferList.mBuffers[0].mDataByteSize; // 设置缓冲区大小
    outBufferList.mBuffers[0].mData           = aacBuf; // 设置AAC缓冲区
    UInt32 outputDataPacketSize               = 1;
    if (AudioConverterFillComplexBuffer(m_converter, inputDataProc, &inBufferList, &outputDataPacketSize, &outBufferList, NULL) != noErr){
        return;
    }
    DDAudioFrame *audioFrame = [[DDAudioFrame alloc] init];
    audioFrame.timestamp = timeStamp;
    audioFrame.nSamplePerSec = self.configuration.audioSampleRate;
    audioFrame.nChannel = self.configuration.numberOfChannels;
    
    NSData *rawAAC = [NSData dataWithBytes:outBufferList.mBuffers[0].mData length:outBufferList.mBuffers[0].mDataByteSize];
    NSData *adtsHeader = [self adtsData:2 rawDataLength:rawAAC.length];
    NSMutableData *fullData = [NSMutableData dataWithData:adtsHeader];
    [fullData appendData:rawAAC];
    audioFrame.data = fullData;
    
    char exeData[2];
    exeData[0] = _configuration.asc[0];
    exeData[1] = _configuration.asc[1];
    
    if(self.aacDeleage && [self.aacDeleage respondsToSelector:@selector(audioEncoder:audioFrame:)]){
        [self.aacDeleage audioEncoder:self audioFrame:audioFrame]; // 数据传出去之后，实现该代理方法，根据后台数据格式进行数据封装，然后发送
    }
}

#pragma mark -- CustomMethod
-(BOOL)createAudioConvert{ //根据输入样本初始化一个编码转换器
    if (m_converter != nil){
        return TRUE;
    }
    
    AudioStreamBasicDescription inputFormat = {0};
    inputFormat.mSampleRate = _configuration.audioSampleRate;
    inputFormat.mFormatID = kAudioFormatLinearPCM;
    inputFormat.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagsNativeEndian | kAudioFormatFlagIsPacked;
    inputFormat.mChannelsPerFrame = (UInt32)_configuration.numberOfChannels;
    inputFormat.mFramesPerPacket = 1;
    inputFormat.mBitsPerChannel = 16;
    inputFormat.mBytesPerFrame = inputFormat.mBitsPerChannel / 8 * inputFormat.mChannelsPerFrame;
    inputFormat.mBytesPerPacket = inputFormat.mBytesPerFrame * inputFormat.mFramesPerPacket;
    
    AudioStreamBasicDescription outputFormat; // 这里开始是输出音频格式
    memset(&outputFormat, 0, sizeof(outputFormat));
    outputFormat.mSampleRate       = inputFormat.mSampleRate; // 采样率保持一致
    outputFormat.mFormatID         = kAudioFormatMPEG4AAC;    // AAC编码 kAudioFormatMPEG4AAC kAudioFormatMPEG4AAC_HE_V2
    outputFormat.mChannelsPerFrame = (UInt32)_configuration.numberOfChannels;;
    outputFormat.mFramesPerPacket  = 1024;                    // AAC一帧是1024个字节
    
    const OSType subtype = kAudioFormatMPEG4AAC;
    AudioClassDescription requestedCodecs[2] = {
        {
            kAudioEncoderComponentType,
            subtype,
            kAppleSoftwareAudioCodecManufacturer
        },
        {
            kAudioEncoderComponentType,
            subtype,
            kAppleHardwareAudioCodecManufacturer
        }
    };
    OSStatus result = AudioConverterNewSpecific(&inputFormat, &outputFormat, 2, requestedCodecs, &m_converter);
    
    if(result != noErr) return NO;
    
    return YES;
}

#pragma mark -- AudioCallBack
OSStatus inputDataProc(AudioConverterRef inConverter, UInt32 *ioNumberDataPackets, AudioBufferList *ioData,AudioStreamPacketDescription **outDataPacketDescription, void *inUserData) {
    AudioBufferList bufferList = *(AudioBufferList*)inUserData;
    ioData->mBuffers[0].mNumberChannels = 1;
    ioData->mBuffers[0].mData           = bufferList.mBuffers[0].mData;
    ioData->mBuffers[0].mDataByteSize   = bufferList.mBuffers[0].mDataByteSize;
    return noErr;
}

/**
 *  Add ADTS header at the beginning of each and every AAC packet.
 *  This is needed as MediaCodec encoder generates a packet of raw
 *  AAC data.
 *
 *  Note the packetLen must count in the ADTS header itself.
 *  See: http://wiki.multimedia.cx/index.php?title=ADTS
 *  Also: http://wiki.multimedia.cx/index.php?title=MPEG-4_Audio#Channel_Configurations
 **/
- (NSData*)adtsData:(NSInteger)channel rawDataLength:(NSInteger)rawDataLength {
    int adtsLength = 7;
    char *packet = malloc(sizeof(char) * adtsLength);
    // Variables Recycled by addADTStoPacket
    int profile = 2;  //AAC LC
    //39=MediaCodecInfo.CodecProfileLevel.AACObjectELD;
    int freqIdx = 4;  //44.1KHz
    int chanCfg = (int)channel;  //MPEG-4 Audio Channel Configuration. 1 Channel front-center
    NSUInteger fullLength = adtsLength + rawDataLength;
    // fill in ADTS data
    packet[0] = (char)0xFF; // 11111111   = syncword
    packet[1] = (char)0xF9; // 1111 1 00 1  = syncword MPEG-2 Layer CRC
    packet[2] = (char)(((profile-1)<<6) + (freqIdx<<2) +(chanCfg>>2));
    packet[3] = (char)(((chanCfg&3)<<6) + (fullLength>>11));
    packet[4] = (char)((fullLength&0x7FF) >> 3);
    packet[5] = (char)(((fullLength&7)<<5) + 0x1F);
    packet[6] = (char)0xFC;
    NSData *data = [NSData dataWithBytesNoCopy:packet length:adtsLength freeWhenDone:YES];
    return data;
}

@end

三、FFLiveKit

如果做视频拉流端既采集音视频、编码、封装、推流，推荐参考FFLiveKit这一框架，很详细，自己看源码就行了，这里就不再赘述。