unilight/seq2seq-vc
A sequence-to-sequence voice conversion toolkit.
This toolkit helps researchers and developers in speech technology convert voices while preserving prosody. You provide source audio, and it outputs the same speech in a different voice. It is specifically designed for those who work on advanced voice conversion techniques, including foreign accent conversion and non-autoregressive models.
108 stars.
Use this if you are a speech researcher or developer working on sequence-to-sequence voice conversion and need a specialized toolkit for advanced experimentation and reproduction of research papers.
Not ideal if you are looking for an out-of-the-box application for simple voice changing without needing to delve into model training or advanced speech processing research.
Stars
108
Forks
15
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/unilight/seq2seq-vc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
index-tts/index-tts
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
stepfun-ai/Step-Audio-EditX
A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing...
lucasnewman/f5-tts-mlx
Implementation of F5-TTS in MLX
FireRedTeam/FireRedTTS
An Open-Sourced LLM-empowered Foundation TTS System
RaduBolbo/F5-TTS-Emotional-CFG
Zero-shot voice cloning text-to-speech (TTS) with explicit emotion class conditioning built on F5-TTS