mrfakename PRO

mrfakename

AI & ML interests

LLMs, TTS, & Open Source

Recent Activity

liked a model about 7 hours ago
Qwen/Qwen3-8B-Base
liked a model about 10 hours ago
kalomaze/Qwen3-16B-A3B
View all activity

Organizations

Notebooks-explorers's profile picture Webhooks Explorers (BETA)'s profile picture Spam Block's profile picture Blog-explorers's profile picture mrfakename's profile picture TTS Models's profile picture TTS Eval (OLD)'s profile picture TTS Arena's profile picture ZeroGPU Explorers's profile picture StyleTTS 2 Demo's profile picture StyleTTS 2 Community's profile picture Unofficial Mistral Community's profile picture OpenPhonemizer's profile picture NeuralVox's profile picture ML for Speech's profile picture CSP-Data's profile picture MLX Community's profile picture Open-Weight Models's profile picture TTS AGI's profile picture Social Post Explorers's profile picture MOS's profile picture OpenRLM's profile picture Dev Mode Explorers's profile picture Hugging Face Discord Community's profile picture test's profile picture OpenMusic's profile picture RefinedSpeech's profile picture Unofficial SI Reuploads's profile picture llamafy's profile picture Speech Data's profile picture OpusLM's profile picture my test org's profile picture test org's profile picture GPUs Cloud's profile picture Unofficial model mirrors for MegaTTS 3's profile picture MoonCast's profile picture TTS AGI External's profile picture Unofficial GLM Community's profile picture Unofficial Wan Community's profile picture Unofficial Qwen Community's profile picture

Posts 15

view post
Post
389
Hi everyone,

I just launched TTS Arena V2 - a platform for benchmarking TTS models by blind A/B testing. The goal is to make it easy to compare quality between open-source and commercial models, including conversational ones.

What's new in V2:

- **Conversational Arena**: Evaluate models like CSM-1B, Dia 1.6B, and PlayDialog in multi-turn settings
- **Personal Leaderboard**: Optional login to see which models you tend to prefer
- **Multi-speaker TTS**: Random voices per generation to reduce speaker bias
- **Performance Upgrade**: Rebuilt from Gradio → Flask. Much faster with fewer failed generations.
- **Keyboard Shortcuts**: Vote entirely via keyboard

Also added models like MegaTTS 3, Cartesia Sonic, and ElevenLabs' full lineup.

I'd love any feedback, feature suggestions, or ideas for models to include.

TTS-AGI/TTS-Arena-V2

Articles 1

Article
64

TTS Arena: Benchmarking Text-to-Speech Models in the Wild