Home
AI Image Gen
AI Chat
3D Splat
Segmentation
Depth Map
Text to Speech
Speech to Text
BG Removal
Vision AI
Image Chat
Object Detect
Upscale
XView Animator
Audio Gen
Stable Audio 3
Text-to-Music in Browser
WASM int4
Loading models (0/4)...
Prompt
Type:
Music
Sound Effect
Ambience
medieval tavern music background
Enhance prompt with AI (~400MB first use, needs ~1GB free RAM)
Duration (s):
Steps:
CFG:
Engine:
auto
hybrid (DiT on CPU)
webgpu only
wasm only (slow)
Seed:
Generate Music
Cancel
Diagnose prompt
Tokenizer
Text Encoder (213 MB)
Number Conditioner (<1 MB)
DiT Transformer (380 MB)
Audio Decoder (45 MB)
⬇ Download WAV
▶
0.0 / 0.0
Latent Shape
--
Audio Length
--
Generation Time
--
Log