Did StyleTTS 2 generate that audio?!?
A demo of OpenDalle V1.1 on a ZERO GPU.
MegaTTS 3 but with voice cloning!
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Demo for OpenF5-TTS
Demo for DMOSpeech 2
Generate a video from audio with customizable waveform visualization
Ultra-fast Whisper Turbo inference ⚡
Dia - 1.6B Text-to-Dialogue Model
Robust, duration-controllable voice-cloning TTS
Unofficial demo for TB-OCR (OCR for documents)
Fast & efficient ASR outperforming Whisper!
Generate MIDI music using RWKV v4!
Experiment26 7B GPU Demo
Crash the current Python application
Generate audio from text
Reconstruct audio using SNAC model
Request a reboot for demo spaces
Sync F5-TTS demo