
Decode and capture
Load WAV, FLAC, or MP3, capture a live device, or read the audio track from a video into an explicit Float32 contract.

Audio
Decode, capture, process, analyze, play, and encode audio through the same matrix runtime that powers OA machine learning.
Pipeline

Load WAV, FLAC, or MP3, capture a live device, or read the audio track from a video into an explicit Float32 contract.

Mix, normalize, resample, saturate, and filter with block-parallel Biquad and 1–64-section SOS processing on the GPU.

STFT, mel spectrograms, and MFCCs produce ordinary Matrix values ready for the Ml stack.

Play, seek, loop, or encode through the same stream contract used by Vision for synchronized media.
Unified media
OA keeps sample metadata, media timestamps, and GPU completion explicit. A decoded video frame and its audio block can be processed independently, synchronized precisely, and written back through the same media layer.
Audio_to_model.rs
1use oa::{audio, Engine};23let engine = Engine::new()?;4let decoded = audio::decode_file(&engine, "speech.flac")?;5let clean = audio::normalize(6 &decoded,7 audio::NormalizeAudioConfig::default(),8)?;9let mel = audio::mel_spectrogram(&clean, audio::MelConfig::default())?;10let output = model.forward(&mel)?;
Capabilities
Decode, transform, synchronize, and deliver without breaking the data model between media, compute, and machine learning.