Never perform heavy computation (file I/O, network requests, GUI updates) inside readData() . It runs on the audio thread. If you block it, you get stuttering and underruns. The Mixer Architecture Most real-world engines need to play multiple sounds simultaneously. Since QAudioSink only outputs a single stream, you must build a software mixer .
Have you built an audio tool with Qt? Let me know about your experience with latency and GStreamer backends in the comments. qt audio engine
For a sequencer or drum machine, do not rely on QTimer . Timers are not accurate enough. Instead, use a QAudioSink with a small buffer size and use the number of bytes processed to calculate the exact playback position in samples. Qt makes network audio surprisingly easy. You can pipe a QNetworkAccessManager reply directly into a buffer. Never perform heavy computation (file I/O, network requests,
When developers think of Qt, they typically imagine polished GUI applications, QML interfaces, or perhaps embedded systems. But lurking beneath the surface of this powerful framework is a surprisingly capable audio module: Qt Multimedia . The Mixer Architecture Most real-world engines need to
class AudioGenerator : public QIODevice { Q_OBJECT public: qint64 readData(char *data, qint64 maxLen) override { // This is called by the audio engine when it needs more data. // You have ~10-50ms to fill this buffer. generateSamples(data, maxLen); return maxLen; } void start() { QAudioFormat format; format.setSampleRate(48000); format.setChannelCount(2); format.setSampleFormat(QAudioFormat::Int16); m_audio = new QAudioSink(format, this); m_audio->start(this); // Qt pulls data automatically } private: QAudioSink *m_audio; };