R
Resemble Enhance
Description
Resemble Enhance is an open model that cleans up speech recordings. It has two parts: a denoiser that separates speech from noisy audio, and an enhancer that improves perceived quality by restoring distortions and extending bandwidth. It is installed with pip and run from the command line on a folder of files; a flag lets you run only the denoiser. The authors say the models were trained on high-quality 44.1 kHz speech. Code and weights are published under the MIT license, the weights are not gated. A web demo is available on Hugging Face Spaces and can also be run locally. The authors do not state hardware requirements or supported languages.
Pros and cons
Pros
- MIT license, commercial use allowed
- Denoiser can be run on its own
- Open weights, no access request
- Web demo on Hugging Face Spaces
Cons
- Hardware requirements are not stated by the authors
- Supported languages are not stated
- Command-line tool, no ready app
Key facts
- License
- MIT
- Commercial use
- Allowed
- Developer
- Resemble AI
- Checked on
- Oct 20, 2026
Editorial score
How strongly the AI Expertise editors recommend this open model for each of its tasks right now, on a 0–10 scale. The score combines output quality, capabilities, ease of launch, license openness and freshness.