VALL-E X
Community open reproduction of Microsoft's multilingual zero shot TTS.
About
VALL-E X is a multilingual text to speech model proposed by Microsoft that extends VALL-E with cross lingual synthesis: a voice prompt in one language can read text in another, alongside zero shot voice cloning, emotion control, and accent control. Microsoft published the research but never released official code or weights.
The usable open release is a from scratch community reproduction by Plachtaa, whose pretrained checkpoint shipped in August 2023 with English, Chinese, and Japanese support, pip installation, and a Vocos decoder upgrade. That provenance matters: treat capability claims as community reported rather than vendor verified, and note the dual use sensitivity of few second voice cloning.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 7/10
Scored 7/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 122; Trending score 68/100 from researcher assessment.