keonlee9420/Robust_Fine_Grained_Prosody_Control
PyTorch Implementation of Robust and fine-grained prosody control of end-to-end speech synthesis
This project helps speech synthesis researchers and developers create natural-sounding spoken audio from text. It takes a text input and a reference speaker's voice, then generates a synthesized speech output that mimics the prosody (rhythm, stress, and intonation) of the reference speaker. It's designed for those working on advanced text-to-speech models.
No commits in the last 6 months.
Use this if you are a speech researcher or developer looking to experiment with fine-grained control over prosody in end-to-end speech synthesis using PyTorch.
Not ideal if you need an out-of-the-box text-to-speech system for production without deep technical involvement or if you don't have access to a powerful GPU.
Stars
41
Forks
11
Language
Python
License
BSD-3-Clause
Category
Last pushed
Feb 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Robust_Fine_Grained_Prosody_Control"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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
unilight/seq2seq-vc
A sequence-to-sequence voice conversion toolkit.
FireRedTeam/FireRedTTS
An Open-Sourced LLM-empowered Foundation TTS System