AI & ML interests
Decentralized yet unified efforts to accelerate research for Open Text to Speech (TTS) systems!
Recent Activity
Articles
TTS Arena V2
Compare two text-to-speech voices and vote for the better
Voice Clone Arena
Vote on the latest Voice Clone TTS models!
Voice Acting Arena
Compare and evaluate two voice performances side by side
Voice Demos
Generate spoken audio from text, with optional voice imitation
TTS Arena Docs
Vote on synthetic voices to rank TTS models
Trajectory Listening Grids
Explore and listen to emotion trajectory audio grids
Trajectory Listening Grids - Voice-Corrected
Listen to corrected emotional speech trajectories side by side
Strict Trajectories - No Voice Conversion
Explore strict‑identity voice chains with crossfaded audio
MOSS voice profiles
Explore emotion‑conditioned speech samples in English & German
Chatterbox Expressive Bestofn
Listen to expressive, high‑quality voice‑clone samples
ACE-Step Vocals-Only LoRA
Generate vocal‑only singing from text prompts
MOSS voice profiles — voice-converted
Explore voice-converted speech across emotions
MOSS Voice Profile — emolia_c1675 (Refined Academic Orator)
Explore emotional speech samples of a refined academic voice
MOSS voice-acting - casting sessions
Generate AI-powered voice acting performances
Majestrino Unified Captions Preview
README
TTS Arena Legacy
Please vote on TTS Arena V2 instead