Stable Audio 3

Esta página da Soniqo documenta Stable Audio 3 conforme a implementação local em speech-swift / speech-core. Os links do Hugging Face ficam abaixo das notas de integração.

Página interna primeiro

Cards e menus apontam primeiro para cá; os links do modelo fonte e dos bundles continuam disponíveis nesta página.

Visão geral

Modelo	Stable Audio 3
Papel	Text-to-music generation
Backend	MLX, Medium DiT int8 default with int4 variant available
Saída	44.1 kHz stereo Float PCM
Idiomas	Prompt language depends on the T5Gemma text encoder
Licença	Stable Audio model terms apply
Status	Default speech compose engine for Stable Audio 3 Medium
Fonte	Stability AI Stable Audio 3
Produto Swift	`StableAudio3MusicGen`
CLI / runtime	`speech compose --engine sa3`

Uso

O trecho abaixo reflete a API ou comando atual exposto por speech-swift.

# Generate 30 seconds of 44.1 kHz stereo audio.
.build/release/speech compose "lofi house loop" \
  --engine sa3 \
  --sa3-variant medium-int8 \
  --seconds 30 \
  -o music.wav

Links do modelo

Notas de implementação

Download is already componentized into DiT, SAME encoder/decoder, and T5Gemma directories; moving it to byte-weighted progress would match the faster Fish path.
Medium DiT uses 24 layers, 1536 hidden size, differential attention, T5Gemma conditioning, and SAME-L decode.
Small Music and Small SFX bundle IDs exist, but the current Swift port wires the Medium family first.
Length is variable: latent steps are ceil(seconds * 44100 / 4096), then output is cropped to the requested duration.