How can I record a conversation phone call on iOS

Question

Theoretically, could an iPhone record a phone call?

I'll take responses that: May or may not call for jailbreaking the phone
Due to the use of private APIs, it might or might not comply with Apple's policies (I don't care; it's not for the App Store).
can or cannot use proprietary SDKs
I don't want replies that are just "Apple does not allow it," to put it clearly. There are call recording apps that route incoming calls through their own servers, but I'm aware there would be no official way to accomplish it, certainly not for an App Store application.

Answer 1

This is for you. complete working illustration The media served daemon needs to have tweak loaded. Every phone call will be recorded and stored in /var/mobile/Media/DCIM/result.m4a. Two channels make up an audio file. The right is the speaker; the left is the microphone. Only when the speaker is activated on an iPhone 4S is a call recorded. On the iPhone 5, 5C, and 5S, all calls are recorded. When switching from speaker to speaker, there can be a few minor difficulties, but the recording will still go on.

#import <AudioToolbox/AudioToolbox.h>
#import <libkern/OSAtomic.h>

//CoreTelephony.framework
extern "C" CFStringRef const kCTCallStatusChangeNotification;
extern "C" CFStringRef const kCTCallStatus;
extern "C" id CTTelephonyCenterGetDefault();
extern "C" void CTTelephonyCenterAddObserver(id ct, void* observer, CFNotificationCallback callBack, CFStringRef name, void *object, CFNotificationSuspensionBehavior sb);
extern "C" int CTGetCurrentCallCount();
enum
{
    kCTCallStatusActive = 1,
    kCTCallStatusHeld = 2,
    kCTCallStatusOutgoing = 3,
    kCTCallStatusIncoming = 4,
    kCTCallStatusHanged = 5
};

NSString* kMicFilePath = @"/var/mobile/Media/DCIM/mic.caf";
NSString* kSpeakerFilePath = @"/var/mobile/Media/DCIM/speaker.caf";
NSString* kResultFilePath = @"/var/mobile/Media/DCIM/result.m4a";

OSSpinLock phoneCallIsActiveLock = 0;
OSSpinLock speakerLock = 0;
OSSpinLock micLock = 0;

ExtAudioFileRef micFile = NULL;
ExtAudioFileRef speakerFile = NULL;

BOOL phoneCallIsActive = NO;

void Convert()
{
    //File URLs
    CFURLRef micUrl = CFURLCreateWithFileSystemPath(NULL, (CFStringRef)kMicFilePath, kCFURLPOSIXPathStyle, false);
    CFURLRef speakerUrl = CFURLCreateWithFileSystemPath(NULL, (CFStringRef)kSpeakerFilePath, kCFURLPOSIXPathStyle, false);
    CFURLRef mixUrl = CFURLCreateWithFileSystemPath(NULL, (CFStringRef)kResultFilePath, kCFURLPOSIXPathStyle, false);

    ExtAudioFileRef micFile = NULL;
    ExtAudioFileRef speakerFile = NULL;
    ExtAudioFileRef mixFile = NULL;

    //Opening input files (speaker and mic)
    ExtAudioFileOpenURL(micUrl, &micFile);
    ExtAudioFileOpenURL(speakerUrl, &speakerFile);

    //Reading input file audio format (mono LPCM)
    AudioStreamBasicDescription inputFormat, outputFormat;
    UInt32 descSize = sizeof(inputFormat);
    ExtAudioFileGetProperty(micFile, kExtAudioFileProperty_FileDataFormat, &descSize, &inputFormat);
    int sampleSize = inputFormat.mBytesPerFrame;

    //Filling input stream format for output file (stereo LPCM)
    FillOutASBDForLPCM(inputFormat, inputFormat.mSampleRate, 2, inputFormat.mBitsPerChannel, inputFormat.mBitsPerChannel, true, false, false);

    //Filling output file audio format (AAC)
    memset(&outputFormat, 0, sizeof(outputFormat));
    outputFormat.mFormatID = kAudioFormatMPEG4AAC;
    outputFormat.mSampleRate = 8000;
    outputFormat.mFormatFlags = kMPEG4Object_AAC_Main;
    outputFormat.mChannelsPerFrame = 2;

    //Opening output file
    ExtAudioFileCreateWithURL(mixUrl, kAudioFileM4AType, &outputFormat, NULL, kAudioFileFlags_EraseFile, &mixFile);
    ExtAudioFileSetProperty(mixFile, kExtAudioFileProperty_ClientDataFormat, sizeof(inputFormat), &inputFormat);

    //Freeing URLs
    CFRelease(micUrl);
    CFRelease(speakerUrl);
    CFRelease(mixUrl);

    //Setting up audio buffers
    int bufferSizeInSamples = 64 * 1024;

    AudioBufferList micBuffer;
    micBuffer.mNumberBuffers = 1;
    micBuffer.mBuffers[0].mNumberChannels = 1;
    micBuffer.mBuffers[0].mDataByteSize = sampleSize * bufferSizeInSamples;
    micBuffer.mBuffers[0].mData = malloc(micBuffer.mBuffers[0].mDataByteSize);

    AudioBufferList speakerBuffer;
    speakerBuffer.mNumberBuffers = 1;
    speakerBuffer.mBuffers[0].mNumberChannels = 1;
    speakerBuffer.mBuffers[0].mDataByteSize = sampleSize * bufferSizeInSamples;
    speakerBuffer.mBuffers[0].mData = malloc(speakerBuffer.mBuffers[0].mDataByteSize);

    AudioBufferList mixBuffer;
    mixBuffer.mNumberBuffers = 1;
    mixBuffer.mBuffers[0].mNumberChannels = 2;
    mixBuffer.mBuffers[0].mDataByteSize = sampleSize * bufferSizeInSamples * 2;
    mixBuffer.mBuffers[0].mData = malloc(mixBuffer.mBuffers[0].mDataByteSize);

    //Converting
    while (true)
    {
        //Reading data from input files
        UInt32 framesToRead = bufferSizeInSamples;
        ExtAudioFileRead(micFile, &framesToRead, &micBuffer);
        ExtAudioFileRead(speakerFile, &framesToRead, &speakerBuffer);
        if (framesToRead == 0)
        {
            break;
        }

        //Building interleaved stereo buffer - left channel is mic, right - speaker
        for (int i = 0; i < framesToRead; i++)
        {
            memcpy((char*)mixBuffer.mBuffers[0].mData + i * sampleSize * 2, (char*)micBuffer.mBuffers[0].mData + i * sampleSize, sampleSize);
            memcpy((char*)mixBuffer.mBuffers[0].mData + i * sampleSize * 2 + sampleSize, (char*)speakerBuffer.mBuffers[0].mData + i * sampleSize, sampleSize);
        }

        //Writing to output file - LPCM will be converted to AAC
        ExtAudioFileWrite(mixFile, framesToRead, &mixBuffer);
    }

    //Closing files
    ExtAudioFileDispose(micFile);
    ExtAudioFileDispose(speakerFile);
    ExtAudioFileDispose(mixFile);

    //Freeing audio buffers
    free(micBuffer.mBuffers[0].mData);
    free(speakerBuffer.mBuffers[0].mData);
    free(mixBuffer.mBuffers[0].mData);
}

void Cleanup()
{
    [[NSFileManager defaultManager] removeItemAtPath:kMicFilePath error:NULL];
    [[NSFileManager defaultManager] removeItemAtPath:kSpeakerFilePath error:NULL];
}

void CoreTelephonyNotificationCallback(CFNotificationCenterRef center, void *observer, CFStringRef name, const void *object, CFDictionaryRef userInfo)
{
    NSDictionary* data = (NSDictionary*)userInfo;

    if ([(NSString*)name isEqualToString:(NSString*)kCTCallStatusChangeNotification])
    {
        int currentCallStatus = [data[(NSString*)kCTCallStatus] integerValue];

        if (currentCallStatus == kCTCallStatusActive)
        {
            OSSpinLockLock(&phoneCallIsActiveLock);
            phoneCallIsActive = YES;
            OSSpinLockUnlock(&phoneCallIsActiveLock);
        }
        else if (currentCallStatus == kCTCallStatusHanged)
        {
            if (CTGetCurrentCallCount() > 0)
            {
                return;
            }

            OSSpinLockLock(&phoneCallIsActiveLock);
            phoneCallIsActive = NO;
            OSSpinLockUnlock(&phoneCallIsActiveLock);

            //Closing mic file
            OSSpinLockLock(&micLock);
            if (micFile != NULL)
            {
                ExtAudioFileDispose(micFile);
            }
            micFile = NULL;
            OSSpinLockUnlock(&micLock);

            //Closing speaker file
            OSSpinLockLock(&speakerLock);
            if (speakerFile != NULL)
            {
                ExtAudioFileDispose(speakerFile);
            }
            speakerFile = NULL;
            OSSpinLockUnlock(&speakerLock);

            Convert();
            Cleanup();
        }
    }
}

OSStatus(*AudioUnitProcess_orig)(AudioUnit unit, AudioUnitRenderActionFlags *ioActionFlags, const AudioTimeStamp *inTimeStamp, UInt32 inNumberFrames, AudioBufferList *ioData);
OSStatus AudioUnitProcess_hook(AudioUnit unit, AudioUnitRenderActionFlags *ioActionFlags, const AudioTimeStamp *inTimeStamp, UInt32 inNumberFrames, AudioBufferList *ioData)
{
    OSSpinLockLock(&phoneCallIsActiveLock);
    if (phoneCallIsActive == NO)
    {
        OSSpinLockUnlock(&phoneCallIsActiveLock);
        return AudioUnitProcess_orig(unit, ioActionFlags, inTimeStamp, inNumberFrames, ioData);
    }
    OSSpinLockUnlock(&phoneCallIsActiveLock);

    ExtAudioFileRef* currentFile = NULL;
    OSSpinLock* currentLock = NULL;

    AudioComponentDescription unitDescription = {0};
    AudioComponentGetDescription(AudioComponentInstanceGetComponent(unit), &unitDescription);
    //'agcc', 'mbdp' - iPhone 4S, iPhone 5
    //'agc2', 'vrq2' - iPhone 5C, iPhone 5S
    if (unitDescription.componentSubType == 'agcc' || unitDescription.componentSubType == 'agc2')
    {
        currentFile = &micFile;
        currentLock = &micLock;
    }
    else if (unitDescription.componentSubType == 'mbdp' || unitDescription.componentSubType == 'vrq2')
    {
        currentFile = &speakerFile;
        currentLock = &speakerLock;
    }

    if (currentFile != NULL)
    {
        OSSpinLockLock(currentLock);

        //Opening file
        if (*currentFile == NULL)
        {
            //Obtaining input audio format
            AudioStreamBasicDescription desc;
            UInt32 descSize = sizeof(desc);
            AudioUnitGetProperty(unit, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Input, 0, &desc, &descSize);

            //Opening audio file
            CFURLRef url = CFURLCreateWithFileSystemPath(NULL, (CFStringRef)((currentFile == &micFile) ? kMicFilePath : kSpeakerFilePath), kCFURLPOSIXPathStyle, false);
            ExtAudioFileRef audioFile = NULL;
            OSStatus result = ExtAudioFileCreateWithURL(url, kAudioFileCAFType, &desc, NULL, kAudioFileFlags_EraseFile, &audioFile);
            if (result != 0)
            {
                *currentFile = NULL;
            }
            else
            {
                *currentFile = audioFile;

                //Writing audio format
                ExtAudioFileSetProperty(*currentFile, kExtAudioFileProperty_ClientDataFormat, sizeof(desc), &desc);
            }
            CFRelease(url);
        }
        else
        {
            //Writing audio buffer
            ExtAudioFileWrite(*currentFile, inNumberFrames, ioData);
        }

        OSSpinLockUnlock(currentLock);
    }

    return AudioUnitProcess_orig(unit, ioActionFlags, inTimeStamp, inNumberFrames, ioData);
}

__attribute__((constructor))
static void initialize()
{
    CTTelephonyCenterAddObserver(CTTelephonyCenterGetDefault(), NULL, CoreTelephonyNotificationCallback, NULL, NULL, CFNotificationSuspensionBehaviorHold);

    MSHookFunction(AudioUnitProcess, AudioUnitProcess_hook, &AudioUnitProcess_orig);
}

A few remarks on the current situation For processing audio streams in order to apply effects, mix, convert, etc., use the AudioUnitProcess function. To gain access to audio streams from phone calls, we are connecting AudioUnitProcess. These streams are being handled in numerous ways while the phone call is in progress.

In order to receive updates on changes to phone call status, we are watching for CoreTelephony messages. We must determine whether audio samples originate from a speaker or a microphone when we get them. The componentSubType field in the AudioComponentDescription structure is used for this. Why not save AudioUnit objects, you could ask, so that we don't constantly have to verify componentSubType? When you turn the iPhone 5's speaker on or off, I did that, however it would cause everything to fail because 

AudioUnit objects are recreated and subject to change. Therefore, we open audio files (one for the speaker and one for the microphone) and enter samples into them. We will receive the proper CoreTelephony message when the phone call is over, and we will close the files. We need to combine two independent audio files that come from the speaker and the microphone. For this purpose, void Convert() is used. If you are familiar with the API, it is fairly easy. I don't think I need to elaborate; the remarks speak for themselves.

regarding locks. Mediaserverd has a lot of threads. We need some sort of synchronisation because CoreTelephony notifications and audio processing are on separate threads. I choose spin locks since they are quick and there is little possibility of lock contention in our situation. The work in AudioUnitProcess on iPhone 4S and even iPhone 5 needs to be completed as quickly as possible in order to avoid glitches coming from the device speaker, which is obviously undesirable.