calls VALL-E-X “Choose it for the historical VALL-E X zero-shot approach, but it's archived.”
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
VALL-E-X is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named VALL-E-X among their alternatives. The relationship is not symmetric — how VALL-E-X rates them is a separate judgement, made when VALL-E-X is analysed in its own right.
calls VALL-E-X “Choose it for the historical VALL-E X zero-shot approach, but it's archived.”
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
calls VALL-E-X “choose for a VALL-E-X approach when you accept an archived, unmaintained implementation.”
Instant voice cloning by MIT and MyShell. Audio foundation model.
calls VALL-E-X “Choose if you want a classic zero-shot TTS implementation, but it is archived and unmaintained.”
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
calls VALL-E-X “choose only for historical reference to VALL-E; it is archived and unmaintained.”
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
calls VALL-E-X “For a zero-shot TTS implementation, but it's archived and older; choose if you need that specific model.”
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
calls VALL-E-X “An older archived zero-shot TTS model; pick only if you specifically need that implementation.”
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.