Stable Audio 3
यह Soniqo पेज स्थानीय speech-swift / speech-core implementation में Stable Audio 3 को दस्तावेज़ करता है। Hugging Face bundle links integration notes के बाद दिए गए हैं।
पहले आंतरिक पेज
Landing cards और docs menus पहले इसी पेज पर आते हैं; source model और bundle links यहीं उपलब्ध रहते हैं।
सारांश
| मॉडल | Stable Audio 3 |
|---|---|
| भूमिका | Text-to-music generation |
| Backend | MLX, Medium DiT int8 default with int4 variant available |
| Output | 44.1 kHz stereo Float PCM |
| भाषाएँ | Prompt language depends on the T5Gemma text encoder |
| लाइसेंस | Stable Audio model terms apply |
| स्थिति | Default speech compose engine for Stable Audio 3 Medium |
| Source | Stability AI Stable Audio 3 |
| Swift product | StableAudio3MusicGen |
| CLI / runtime | speech compose --engine sa3 |
उपयोग
नीचे का snippet मौजूदा speech-swift API या command से मेल खाता है।
# 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.wavमॉडल लिंक
implementation notes
- 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.