DiffRhythm

Web · Windows · Mac · Linux · Self-hosted

Freedom report

Two barsScore 6.3

Runs widely4 of 6 device platforms
DocumentedPlans, terms and facts published

DiffRhythm is ranked #79 of 124 in AI music generators on Freedom251. It runs on Linux, macOS, Self-hosted, Web, Windows.

Compared on AI music generators

Commercial use: Yes
Vocal generation: Yes
Audio upload: Yes
Audio export formats: wav

Best DiffRhythm alternatives

See all 20

One bar Suno Free tier No. 1$8/mo8.1 One bar Eleven Music Free tier No. 2$6/mo8.0 One bar Udio Free tier No. 3$10/mo7.9 One bar MusicWave.ai Free tier No. 4$5.99/mo7.9 One bar Solos Music Free tier No. 5Free7.9 Two bars Treblo Free tier No. 6Free7.9

The record

Purpose: DiffRhythm is an open-source diffusion music model designed to generate full-length songs.
Song length: The listed base models generate 1 minute 35 second songs, and the full models generate 4 minute 45 second songs.
Input modes: The project describes text-based style prompts, instrumental generation, and generation using a reference WAV file.
Editing: The project says version 1.2 enables song editing and continuation and improves its handling of music structure and style.
Installation: The repository provides local inference instructions for Linux, macOS, and Windows, and includes Docker installation instructions.
Hardware requirement: DiffRhythm-base requires at least 8 GB of VRAM; the repository says chunked decoding can help meet this requirement.
License: The code and DiT weights are released under Apache License 2.0, which allows use, modification, and distribution subject to its notices and disclaimer.
Pricing: The project says its makers do not make a profit from the model; the page lists no paid plans or prices.
Training: The repository says training is coming soon.
Responsible use: The makers advise users to verify musical originality, disclose AI involvement, and obtain permissions when adapting protected styles.
Support: The repository invites messages to the research team at [email protected].
Intended users: The project describes itself as a foundation for research and development and says it supports artistic creation, education, and entertainment.
What it does: DiffRhythm is an open-source diffusion model for generating full-length songs.
Inputs and modes: It supports text-based style prompts, instrumental generation, and inference using a reference WAV or a text prompt reference.

Where it ranks on Freedom251

Best AI Music Generators in 2026#79 of 124

Is DiffRhythm yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote DiffRhythm

Sources

github.com/ASLP-lab/DiffRhythm· checked 12 Oct 2026