keonlee9420/Daft-Exprt
PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
This project helps create expressive speech by taking written text and an audio sample, then generates new speech that sounds like the provided text, but with the specific voice and speaking style (prosody) from the audio sample. It's useful for content creators, audiobook producers, or anyone needing consistent, emotionally varied voiceovers from text. The output is synthesized audio with transferred prosody.
No commits in the last 6 months.
Use this if you need to generate speech from text while maintaining the expressive style, pitch, and rhythm of a specific reference audio, even across different speakers.
Not ideal if you need a simple text-to-speech system without advanced prosody control or if you are not comfortable with command-line tools.
Stars
55
Forks
13
Language
Python
License
MIT
Category
Last pushed
Oct 15, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Daft-Exprt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowTTS
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for...
lucasnewman/nanospeech
A simple, hackable text-to-speech system in PyTorch and MLX
Tomiinek/Multilingual_Text_to_Speech
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing,...
keonlee9420/STYLER
Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech...
jxzhanggg/nonparaSeq2seqVC_code
Implementation code of non-parallel sequence-to-sequence VC