Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
mrfakenameย 
posted an update Apr 30
Post
2604
Excited to launch two new SOTA text-to-speech models on the TTS Arena:

- OpenVoice V2
- Play.HT 2.0

๐—”๐—ฏ๐—ผ๐˜‚๐˜ ๐˜๐—ต๐—ฒ ๐—ง๐—ง๐—ฆ ๐—”๐—ฟ๐—ฒ๐—ป๐—ฎ

The TTS Arena is an open sourced Arena where you can enter a prompt, have two models generate speech, and vote on which one is superior.

We compile the results from the votes into a automatically updated leaderboard to allow developers to select the best model.

We've already included models such as ElevenLabs, XTTS, StyleTTS 2, and MetaVoice. The more votes we collect, the sooner we'll be able to show these new models on the leaderboard and compare them!

๐—ข๐—ฝ๐—ฒ๐—ป๐—ฉ๐—ผ๐—ถ๐—ฐ๐—ฒ ๐—ฉ๐Ÿฎ

OpenVoice V2 is an open-sourced speech synthesis model created by MyShell AI that supports instant zero-shot voice cloning. It's the next generation of OpenVoice, and is fully open-sourced under the MIT license.
https://github.com/myshell-ai/OpenVoice

๐—ฃ๐—น๐—ฎ๐˜†.๐—›๐—ง ๐Ÿฎ.๐Ÿฌ

Playโ€คHT 2.0 is a high-quality proprietary text-to-speech engine. Accessible through their API, this model supports zero-shot voice cloning.

๐—–๐—ผ๐—บ๐—ฝ๐—ฎ๐—ฟ๐—ฒ ๐˜๐—ต๐—ฒ ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น๐˜€ ๐—ผ๐—ป ๐˜๐—ต๐—ฒ ๐—ง๐—ง๐—ฆ ๐—”๐—ฟ๐—ฒ๐—ป๐—ฎ:

TTS-AGI/TTS-Arena
In this post