Neiro
github.com
- Free plan
- Windows
- macOS
- Linux
- Web
- Self-hosted
What Neiro is
Neiro is a free audio worksuite for source separation, restoration, transcription and editing that processes audio on the user's machine. It offers a Tauri desktop app and a browser interface launched with `neiro ui`; desktop installers are listed for Windows, macOS and Linux. Separation can isolate vocals, instrumentals, harmonic and percussive parts, four- or six-stem mixes, and drum kits, with a null-test residual for each result. Restoration tools cover declipping, hum removal, denoising, dereverberation, bandwidth extension and reference mastering. Transcription can produce MIDI, MusicXML, ASCII tablature and LRC lyrics. Studio provides non-destructive waveform edits, while Learn includes practice features such as loop regions, count-in, metronome, step mode, WebMIDI and DAW wait mode. VST2 and CLAP injectors can capture audio from a DAW. Core DSP does not require model downloads; neural backends are optional. The interface binds to 127.0.0.1, with no outbound network activity by default apart from user-initiated model downloads and updates. The Python package requires Python 3.10–3.12; compressed or video inputs require ffmpeg on PATH.
Who it suits
Neiro suits audio creators who want local tools for separation, cleanup, transcription, editing or practice. Users choosing neural models should review each model's license, and users of compressed or video inputs need ffmpeg on PATH.
Good to know, and what to watch
- Audio processing stays on the user's machine.
- Core DSP works without model downloads.
- Supports separation, restoration, transcription and editing.
- VST2 and CLAP injectors can capture DAW audio.
- Python package requires Python 3.10–3.12.
- Compressed or video inputs require ffmpeg on PATH.
- Some model licenses are non-commercial or research-only.
- Granted Python adapters run without a sandbox.
Getting started
- Open the Neiro GitHub project
- Install the Windows, macOS or Linux desktop release, or install the Python package
- Use WAV or FLAC directly, or place ffmpeg on PATH for compressed and video inputs
- Launch the browser interface with `neiro ui`
- Download optional neural models when needed
- Connect a DAW through the documented VST2 or CLAP injector
Limits to check
Core DSP works without models, but optional neural backends download weights on first use. Individual model licenses may impose non-commercial or research-only restrictions, and Python use requires version 3.10–3.12.
The verdict
Neiro combines local audio processing with a broad set of separation, restoration, transcription and practice tools. Check model licensing and the input requirements before choosing optional backends or processing compressed and video files.
Questions people ask
Is Neiro free?
Yes. Neiro is listed as free and has a free plan.
Where is audio processed?
Audio is processed on the user’s machine and does not leave it.
Which systems have desktop installers?
The release page lists Windows MSI/EXE, macOS DMG and Linux AppImage/DEB installers.
What can Neiro export from transcription?
It can export MIDI, MusicXML, ASCII tablature and LRC lyrics.
Does it work with a DAW?
VST2 and CLAP injectors can capture audio into Neiro’s interface, and a VST2 pass-through injector is documented.
Are models included?
Neural weights are not bundled with desktop releases; they download on first use and retain their own licenses.
What the maker publishes
- DAW integration
- Shared-window VST2 and CLAP injectors can capture audio into Neiro's interface. source
- Desktop downloads
- The release page lists Windows MSI/EXE, macOS DMG, and Linux AppImage/DEB installers. source
- Editing and practice
- Its Studio supports non-destructive audio edits, while Learn offers loop regions, count-in, metronome, WebMIDI, and DAW wait mode. source
- Evaluation limits
- Full MUSDB18-HQ and MAESTRO evaluation numbers require user-provisioned datasets. source
- Extension limits
- Neiro documents a local Python adapter plugin MVP, but granted adapters run in the Neiro process without a sandbox. source
- Integrations
- The project documents VST2 and CLAP injectors for shared-window DAW capture, and a VST2 effect that works as a pass-through injector in a DAW. source
- Interfaces
- Neiro provides a Tauri desktop app and a browser interface launched with `neiro ui`. source
- Interfaces
- The worksuite is available as a Tauri desktop app or through `neiro ui` in a browser, using the same modules and local cache. source
- License
- The engine, desktop shell, and frontend are MIT licensed; individual models retain their own licenses, some of which are non-commercial or research-only. source
- License
- The repository license is MIT for the Neiro engine source, while model weights have separate licenses. source
- Local interface security
- The UI binds to 127.0.0.1, and the desktop shell restricts its connections to the local engine origin. source
- Local network boundary
- The interface binds to 127.0.0.1, and the security policy says the app has no outbound network activity by default apart from user-initiated model downloads and updates. source
- Local processing
- Audio is processed on the user's machine and does not leave it. source
- Local processing
- The maker says audio is processed locally and not transmitted; outbound network activity is limited to user-initiated model downloads and application updates. source
- Model downloads and licensing
- Neural weights are not bundled with desktop releases and download on first use; each model carries its own license, which can include non-commercial or research-only terms. source
- Model options
- The core DSP floor works without model downloads; neural backends such as Demucs, Basic Pitch, and AudioSR are optional. source
- Model security
- Model weight downloads are checked against manifest SHA-256 values, and the security policy warns that third-party weights can be dangerous. source
- Purpose
- Neiro is a local worksuite for audio source separation, restoration, transcription, and editing. source
- Purpose
- Neiro is a local audio worksuite for source separation, restoration, transcription, and audio editing. source
- Requirements
- The Python package requires Python 3.10–3.12, and compressed or video inputs require ffmpeg on PATH; WAV and FLAC work without it. source
- Restoration
- Restoration features include declipping, hum removal, denoising, dereverberation, bandwidth extension, and reference mastering. source
- Restoration
- Its restoration features include declipping, hum removal, denoising, dereverberation, bandwidth extension, and reference mastering. source
- Separation
- It separates vocals, instrumentals, harmonic/percussive parts, four- or six-stem mixes, and drum kits, with a null-test residual for each result. source
- Separation
- It separates vocals, karaoke, harmonic and percussive parts, and 4- or 6-stem audio, and provides a null-test residual. source
Checked against the maker's pages on 30 Sept 2026.