hash2430/pitchtron
TTS for pitch-accented language. Korean dialect DB.
This tool helps you create natural-sounding speech in various Korean dialects and emotional styles from standard, neutral voice recordings. It takes an input text and a reference audio with the desired speaking style (like a Kyongsang dialect speaker or an excited voice), then generates that text spoken in a target voice with the reference's prosody. Voice actors, content creators, or language educators who need to generate stylized Korean speech, especially in specific dialects, would find this useful.
157 stars. No commits in the last 6 months.
Use this if you need to generate Korean speech with specific dialects or emotional tones, even when your training data only contains standard, neutral voices.
Not ideal if you require strict, unnatural pitch control that might go beyond a natural-sounding vocal range.
Stars
157
Forks
29
Language
Python
License
—
Category
Last pushed
May 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/hash2430/pitchtron"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bshall/Tacotron
A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Kyubyong/dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
DemisEom/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Rayhane-mamah/Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model