Home/Speech & Audio/DiffSinger

DiffSinger

MoonInTheRiver/DiffSinger

Singing Voice Synthesis via Shallow Diffusion Mechanism

GitHub

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

72views this month

4.9k stars826 forksLast push Jul 24, 2026 Python MIT

Decision brief

DiffSinger leverages a shallow diffusion mechanism for high-quality singing voice synthesis and text-to-speech (TTS) tasks. It supports both ground-truth F0-based singing synthesis and explicit pitch prediction in TTS.

Good fit when

Need precise control over the fundamental frequency (F0) when synthesizing singing voices
Seeking a project with support for specific datasets like PopCS for SVS

Avoid when

In need of real-time synthesis performance due to the resource demands of diffusion mechanisms
Looking for an end-to-end model that does not require ground-truth F0 information for SVS tasks

Observed Jul 17, 2026 · Source: enrich:decision_facts

DiffSinger alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Steady (57d since push); As of Sep 20, 2026
Provenance: Not a fork · Personal account; As of Sep 20, 2026
Security (OSV): 24 low (24 low); As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install DiffSinger

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

GPT-SoVITS

Voice Cloning and Text-to-Speech with Minimal Voice Data

62k★

VoxCPM

Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

38k★

MockingBird

Clone a voice in 5 seconds to generate arbitrary speech in real-time

37k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

DiffSinger is a singing voice synthesis project that uses a shallow diffusion mechanism for SVS and TTS tasks.

Capability facts

Languages: python
Source: github.language · Sep 20, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Sep 20, 2026)

conda create -n your_env_name python=3.8

Source link

README

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism This repository is the official PyTorch implementation of our AAAI 2022 paper, in which we propose DiffSinger (for Singing Voice Synthesis) and DiffSpeech (for Text to Speech). :tada: :tada: :tada: Updates : Sep....

For agents

This page has a .md twin and JSON over the API.

/tools/moonintheriver-diffsinger.md GET /api/graphcanon/tools/moonintheriver-diffsinger GET /api/graphcanon/graph?tool=moonintheriver-diffsinger