Search code examples
iosaudiocodecopus

How to encode and decode audio using opus


I am trying integrate opus into my application, the encode and decode function returns positive value which means successfully, but the output audio can't play. Raw audio data can play as well. Here is how I encode data. I use 4 bytes prefix to separate from each packet.

self.encoder = opus_encoder_create(24000, 1, OPUS_APPLICATION_VOIP, &opusError);
opus_encoder_ctl(self.encoder, OPUS_SET_BANDWIDTH(OPUS_BANDWIDTH_SUPERWIDEBAND));



- (void) encodeBufferList:(AudioBufferList *)bufferList {
    BOOL success = TPCircularBufferProduceBytes(_circularBuffer, bufferList->mBuffers[0].mData, bufferList->mBuffers[0].mDataByteSize);
    if (!success) {
        NSLog(@"insufficient space in circular buffer!");
    }

    if (!_encoding) {
            _encoding = YES;

            dispatch_async(self.processingQueue, ^{
                [self startEncodingLoop];
            });
    }
}


-(void)startEncodingLoop
{
    int32_t availableBytes = 0;
    opus_int16 *data = (opus_int16*)TPCircularBufferTail(_circularBuffer, &availableBytes);
    int availableSamples = availableBytes / _inputASBD.mBytesPerFrame;

    /*!
     *  Use dynamic duration
     */
//    int validSamples[6] = {2.5, 5, 10, 20, 40, 60}; // in milisecond
//    int esample = validSamples[0] * self.sampleRate / 1000;
//    for (int i = 0; i < 6; i++) {
//        int32_t samp = validSamples[i] * self.sampleRate / 1000;
//        if (availableSamples < samp) {
//            break;
//        }
//        esample = samp;
//    }

    /*!
     *  Use 20ms
     */
    int esample = 20 * self.sampleRate / 1000;

    if (availableSamples < esample) {
        /*!
         *  Out of data. Finish encoding
         */
        self.encoding = NO;
        [self.eDelegate didFinishEncode];
        return;
    }

//    printf("raw input value for packet \n");
//    for (int i = 0; i < esample * self.numberOfChannels; i++) {
//        printf("%d :", data[i]);
//    }

    int returnValue = opus_encode(_encoder, data, esample, _encoderOutputBuffer, 1000);

    TPCircularBufferConsume(_circularBuffer, esample * sizeof(opus_int16) * self.numberOfChannels);

//    printf("output encode \n");
//    for (int i = 0; i < returnValue; i++) {
//        printf("%d :", _encoderOutputBuffer[i]);
//    }

    NSMutableData *outputData = [NSMutableData new];
    NSError *error = nil;
    if (returnValue <= 0) {
        error = [OKUtilities errorForOpusErrorCode:returnValue];
    }else {
        [outputData appendBytes:_encoderOutputBuffer length:returnValue * sizeof(unsigned char)];
        unsigned char int_field[4];
        int_to_char(returnValue , int_field);
        NSData *header = [NSData dataWithBytes:&int_field[0] length:4 * sizeof(unsigned char)];
        if (self.eDelegate) {
            [self.eDelegate didEncodeWithData:header];
        }
    }

    if (self.eDelegate) {
        [self.eDelegate didEncodeWithData:outputData];
    }

    [self startEncodingLoop];
}

And here is decode function:

self.decoder = opus_decoder_create(24000, 1, &opusError);
opus_decoder_ctl(self.decoder, OPUS_SET_SIGNAL(OPUS_SIGNAL_VOICE));
opus_decoder_ctl(self.decoder, OPUS_SET_GAIN(10));


-(void)startParseData:(unsigned char*)data remainingLen:(int)len
{
    if (len <= 0) {
        [self.dDelegate didFinishDecode];
        return;
    }
    int headLen = sizeof(unsigned char) * 4;
    unsigned char h[4];
    h[0] = data[0];
    h[1] = data[1];
    h[2] = data[2];
    h[3] = data[3];

    int packetLen = char_to_int(h);
    data += headLen;
    packetLen = packetLen * sizeof(unsigned char) * self.numberOfChannels;
    [self decodePacket:data length:packetLen remainingLen:len - headLen];
}

-(void)decodePacket:(unsigned char*)inputData length:(int)len remainingLen:(int)rl
{
    int bw = opus_packet_get_bandwidth(inputData); //TEST: return OPUS_BANDWIDTH_SUPERWIDEBAND here
    int32_t decodedSamples = 0;

//    int validSamples[6] = {2.5, 5, 10, 20, 40, 60}; // in milisecond
    /*!
     *  Use 60ms
     */
    int esample = 60 * self.sampleRate / 1000;
//    printf("input decode \n");
//    for (int i = 0; i < len; i++) {
//        printf("%d :", inputData[i]);
//    }

    _decoderBufferLength = esample * self.numberOfChannels * sizeof(opus_int16);
    int returnValue = opus_decode(_decoder, inputData, len, _outputBuffer, esample, 1);
    if (returnValue < 0) {
        NSError *error = [OKUtilities errorForOpusErrorCode:returnValue];
        NSLog(@"decode error %@", error);
        inputData += len;
        [self startParseData:inputData remainingLen:rl - len];
        return;
    }
    decodedSamples = returnValue;

    NSUInteger length = decodedSamples * self.numberOfChannels;

//    printf("raw decoded data \n");
//    for (int i = 0; i < length; i++) {
//        printf("%d :", _outputBuffer[i]);
//    }

    NSData *audioData = [NSData dataWithBytes:_outputBuffer length:length * sizeof(opus_int16)];
    if (self.dDelegate) {
        [self.dDelegate didDecodeData:audioData];
    }
    inputData += len;
    [self startParseData:inputData remainingLen:rl - len];
}

Please help me to point out what I am missing. An example would be great.


Solution

  • I found what the problem is. I have set the audio format is float kAudioFormatFlagIsPacked|kAudioFormatFlagIsFloat;. I should use opus_encode_float and opus_decode_float instead of opus_encode opus_decode. As @Ralph says, we should use fec = 0 in opus_decode. Thanks to @Ralph.