maum-ai/assem-vc
Official Code for Assem-VC @ICASSP2022
This project helps convert a spoken or sung voice into the voice of a different speaker while preserving the original speech content or melody. You provide an audio recording of someone speaking or singing, and it outputs the same content in the voice of a different person you specify. This is ideal for content creators, audio producers, or anyone needing to generate speech or singing in multiple distinct voices without re-recording.
269 stars. No commits in the last 6 months.
Use this if you need to transform spoken dialogue or singing performances into a different voice while maintaining the original delivery and emotion.
Not ideal if you need to create entirely new speech from text or generate voices that don't yet exist, as it focuses on converting existing audio.
Stars
269
Forks
38
Language
Jupyter Notebook
License
BSD-3-Clause
Category
Last pushed
May 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/maum-ai/assem-vc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment