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 .

For 80% of applications—media players, notification systems, game sound effects, or simple synthesizers—Qt Multimedia is the fastest way to ship audio on Windows, macOS, Linux, Android, and iOS from a single codebase. Just remember to keep your audio callbacks lean, mix manually, and always respect the hardware's native format.

Have you built an audio tool with Qt? Let me know about your experience with latency and GStreamer backends in the comments.

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; };