The encoder half of the stabilityai/stable-audio-3-small-music autoencoder, exported to ONNX so audio can be turned into latents in the browser via onnxruntime-web.

It is the missing counterpart to the decoder in lsb/stable-audio-3-small-music-onnx: the decoder maps latents → audio, this maps audio → latents. Together they enable audio-to-audio (variation), inpainting, and continuation on top of that text-to-music bundle.

The encode path is patchify (patch_size=256) → SAME encoder (taae_v2) → softnorm bottleneck. Linear/MatMul weights are quantized to int4 MatMulNBits (block_size=32, symmetric); convolutions and norms stay fp32. Single file, no external data.

input   audio    float32  (1, 2, N)        stereo, 44.1 kHz, N a multiple of 8192
output  latents  float32  (1, 256, N/4096) same latent space as the decoder's input

N must be a multiple of 8192 samples (the model's audio_align, so the latent length t_lat = N/4096 is even). Pad shorter clips with zeros; the latent is laid out in time, so you can trim trailing latent frames that correspond to the padding.

Measured as the full round-trip ONNX encoder → the q4 browser decoder on a real clip:

The int4 export is bit-faithful to the fp32 graph except for the quantized weights (latent correlation 0.978 vs fp32). For variation/img2img the encoder latent is re-noised and refined by the diffusion sampler, so the int4 precision loss is not audible in practice.

Inherits the Stability AI Community License from the upstream weights; the bundled T5Gemma text encoder (used elsewhere in the pipeline) additionally falls under Google's Gemma Terms of Use. This repo contains only the audio autoencoder's encoder.