Stable Audio Live Multiplayer
Generate custom audio from a text prompt
Generate custom audio from a text prompt
Generate audio from text with voice cloning
Transcribe audio to text using your browser's GPU
Generate music from text and optional melody
Transcribe audio and generate responses based on prompts
Generate multi‑speaker AI podcasts from a script
Generate speech in a custom voice from reference audio
Generate expressive speech from your text in seconds
Generate speech from text using a voice model
Audio Flamingo 3 Demo
Try out Step-Audio-EditX
Transcribe audio/video files into text instantly
Interactive guide to audio reasoning and Step-Audio-R1 model
Chat with an AI using text, images, and videos
Fast Editing with Robust Consistency
Transcribe audio recordings into written text
Streaming conversational audio in realtime
Generate speech from text with voice design, cloning, or presets
DeepSeek-OCR 2: Visual Causal Flow
Generate singing voice from lyrics or convert voices
ZeroGPU Nano-TTS voice clone demo
VoxCPM2 Nano-vLLM Demo
Audio and text demo for NVIDIA Nemotron-Labs-Audex-2B.
Blazingly fast text-to-speech 100% locally in your browser!
Kitten TTS 2, plus Mini, Nano and Pico on CPU
TTS models that run on CPU (4M & 9M parameters)
Create natural‑sound speech from your text
Generate speech using a cloned voice from your audio sample
Bilingual TTS with voice design, cloning, and direction
VoxCPM2 voice server for Aster