lifeiteng/vall-e
PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html
Implements a two-stage autoregressive-then-non-autoregressive decoder architecture that leverages neural codec tokens for speaker-preserving synthesis, trainable on a single GPU. Integrates with the Lhotse dataset framework and k2/Icefall speech processing toolkit for phoneme tokenization, feature extraction, and dataset preparation. Supports both English (LibriTTS) and Mandarin Chinese (AISHELL-1) with configurable acoustic prompt strategies during training.
2,207 stars. No commits in the last 6 months.
Stars
2,207
Forks
334
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/lifeiteng/vall-e"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
canopyai/Orpheus-TTS
Towards Human-Sounding Speech
Plachtaa/VALL-E-X
An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in...
umbertocappellazzo/Omni-AVSR
Official Pytorch implementation of "Omni-AVSR: Towards Unified Multimodal Speech Recognition...
primepake/learnable-speech
This repo is text to speech with learnable audio encoder without alignment with transcript reference
ExplainableML/ZerAuCap
[NeurIPS 2023 - ML for Audio Workshop (Oral)] Zero-shot audio captioning with audio-language...