pinned
Running
NanoMaestro Realtime
πΉ
Generate endless realβtime music locally on any CPU
mu
yumu908
Β·
AI & ML interests
None yet
Recent Activity
updated a Space 21 days ago
yumu908/Supertonic-TTS-WebGPU updated a Space 22 days ago
yumu908/Voxtral-Realtime-WebGPU updated a Space 2 months ago
yumu908/ZipVoiceOnnxOrganizations
None yet
pinned
Paused
Agents
change clothes
π
Generate virtual tryβon image of a person wearing a garment
Paused
Supertonic TTS WebGPU
β‘
Blazingly fast text-to-speech 100% locally in your browser!
Running
Voxtral Realtime WebGPU
π¬
Real-time speech transcription, entirely in your browser.
Running
Fruit Fly Simulation
πͺ°
Simulate a fruit fly in your browser using WebGPU kernels
Running
1
VibeVoice ASR Streaming
π
Official Playground of Microsoft VibeVoice-ASR-Streaming
Running
Granite Speech Streaming Webgpu
π
Granite Speech 5.0 Turbo CTC Streaming Audio Demo
Paused
Agents
Menriq Virtual Tryon
π
AI virtual try-on for MENRIQ fashion products
Paused
Agents
Remove AI Watermarks
π§Ό
Identify provenance, remove visible AI marks, strip metadata
Paused
HF Realtime Voice
π
Voice chat over WebSocket against a HF speech-to-speech
Running
Web Assembly Vad Sherpa Onnx
π’
Detect speech segments in real-time from microphone
Running
Realtime Vocal Remover
π
Real-time vocal removal & 3-band audio equalizer
Running
PrimeTTS Streaming WASM
π
Real-time streaming zh-TW + English TTS (WASM, no server)
Paused
Agents
TryON Virtual Try-On
π
Generate a virtual tryβon image of a person wearing a garment
Paused
Agents
1
ZipVoice ONNX
π
Running
Pocket TTS ONNX Web Demo
π
Multilingual Pocket TTS voice cloning in the browser (CPU)
Paused
HF Realtime Voice + Avatar
π
Voice chat with a lip-synced 3D avatar, open s2s stack
Paused
MCP
MimiLens Watermark Detector
π
Detect watermarks, signatures, and artifacts in images
Running
MOSS-TTS-Nano Β· ζ΅θ§ε¨θ―ι³εζ
π²
ζ΅θ§ε¨ζ΅εΌ TTSοΌιΆδΈδΌ Β· Browser TTS, local
Paused
Agents
Flux Kontext TryOn
β‘
Try-on model based on Flux Kontext and LoRA
Running
Supertonic 3 (TTS)
β‘
Lightning-Fast, On-Device, Multilingual, Accurate TTS
Running
Web Assembly Asr Sherpa Onnx Zh En
π
Running
Voxtral Realtime 4B
π
Speech-to-Text in the browser with transformers.js + WebGPU
Paused
Agents
Invisible Watermark Against Unauthorized AI Training β Text, Image & Video Protection
β‘
One embed. Four invisible layers. 34 attacks defeated.