Best TTS framework/model for accurate cloning? (Don't care about speed)

[ashen sequoia]

Among models like:

• TorToiSe
• Coqui XTTS
• StyleTTS2
• Bark
• Openvoice
• etc.

Which one has the highest quality in terms of accurately replicating the voice and speaking style of the sample? (Intonation, emotion, expressive range, etc.)

[viscid echo]

https://youtu.be/7tpWH8_S8es?si=nCqH4uTby_K7682c this guy made a web ui for tortoise tts and rvc and its sounds pretty good and expressive

Never tried the others one tho so i dont know if they are any better

[ashen sequoia]

Have you personally tried tortoise?

[viscid echo]

Nope but i say give it a shot

[tulip talon]

btw if you wanthere some tts #1212368971127590922