KyungsuKim42/tokensynth
The official implementation of TokenSynth (ICASSP 2025)
This tool helps music producers, sound designers, and composers create new instrument sounds or mimic existing ones. You provide a MIDI file for the musical notes, and either a reference audio recording of an instrument, a text description of a timbre, or both, to generate brand new musical audio. It's for anyone who needs to quickly design unique instrument sounds without extensive manual synthesis.
Available on PyPI.
Use this if you want to generate realistic or stylized instrument sounds from MIDI, either by cloning the timbre of an audio example or by describing a desired sound with text.
Not ideal if you need to synthesize full multi-instrument compositions or vocals, as it focuses specifically on polyphonic single-instrument audio.
Stars
81
Forks
4
Language
Python
License
MIT
Category
Last pushed
Oct 27, 2025
Commits (30d)
0
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/KyungsuKim42/tokensynth"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
descriptinc/descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz...
drethage/speech-denoising-wavenet
A neural network for end-to-end speech denoising
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
iver56/torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
lmnt-com/wavegrad
A fast, high-quality neural vocoder.