I've been loving the app. The audio restoration works amazing on my suno songs
Remove TV Show Sound Effects and Keep Only Music
Clean old TV and movie recordings by removing laugh tracks, crowd cheering, foley, and dialog while preserving the music bed.
Or
Upload audio files
Free accounts can upload files up to 50MB.
How to Keep Only Music from TV Audio
Upload
Upload your TV or movie audio extract
Prompt the Model
You start with 'music with vocals' prefilled. If needed, select the noisy section and describe the noise to remove.
Download Stems
Get a music-focused stem plus an isolated noise/effects stem for full control in post.
Example: Star Trek Scene with Mixed SFX and Dialog
Hear the original mixed soundtrack, then the extracted music-focused output, then the isolated noise/effects stem.
Example: Live show with Laughing Tracks and Foley
The laughter, impacts, and scene sound effects are isolated so you can keep mostly the music layer.
Prompt-Based SFX Removal
SAM Audio lets you target crowd noise, laugh tracks, foley, hissing, rumbling, and other specific artifacts.
Section-Aware Cleanup
For best precision, select the exact section where noise appears and describe it, such as knocking, pounding, thumping, rumbling, or hissing.
Keep Music Character
Preserve the tone and stereo feel of the soundtrack while separating unwanted effects and spoken lines.
Trusted by 15,000+ music lovers
Neural Analog makes me feel like a monkey with an AK-47, in the best way possible
It worked! Well done :) Many thanks :))))
Wow thank you so much i upscale videos and take out live recordings from music because of my autism i hate the crowd
Amazing tool for audio. Clean, simple, and effective. I would spend hours in RX to get the same results. Give it a try. I can save you hours of production time.
H
Hasina
4 out of 5 stars
Useful app besides AudioSR that needs improvement for AI vocals high frequencies restoration. It sometimes adds a straight line at 10kHz or reduces the 5-10kHz volume. I only got the right correction on my 5th restoration of the same vocal.
TG
The Grim Tower
5 out of 5 stars
Love it! Makes everything crisp!
SH
Shrunken Head
5 out of 5 stars
IT'S GREAT
F
Francisco
5 out of 5 stars
Sensacional
TS
Tommi, Studionet
5 out of 5 stars
Highend services!
Listen to tracks made by our users
AI audio enhanced with Neural Analog
Why This Works Better Than Basic EQ and Noise Gates
In old TV and movie mixes, dialog, crowd reactions, and foley often overlap the same frequencies as music. EQ and gates usually damage both. SAM Audio uses prompt-based source separation, so you can describe what should stay and what should be isolated.
Useful for Archival, Remastering, and Sampling
Extract Music Beds
Pull out music from episodes or scenes where isolated score stems are unavailable.
Reduce Spoken Interference
Minimize voiceover lines and dialog in music-heavy scenes to recover cleaner backing tracks.
Isolate Foley and Crowd Layers
Capture laughter, cheering, and foley as a separate stem when you need to rebalance or replace them.
Prepare Better Restorations
Start restoration and remastering from cleaner stems instead of a permanently baked final mix.
Frequently Asked Questions
When you extract the stem with Neural Analog, you'll receive both the separated music track and the isolated crowd noise track. You can keep just the crowd noise if that's what you need.
It can clean up loud live recordings. The model separates audience noise (cheering, clapping, talking) from musical content to isolate a cleaner music track.
Yes. Extract with a bird/ambience-removal prompt to get a cleaner stem with only instruments and vocals emphasized, while the ambience is routed to a separate stem.
With the custom prompt option, you can describe any instrument you want to isolate (e.g., "saxophone", "synthesizer", "electric guitar"). The SAM Audio model uses your description to separate that specific sound from the mix, giving you flexibility beyond standard presets.
Mid/Sides processing helps preserve stereo width while isolating centered and side information more cleanly. This usually keeps instruments natural and avoids collapsing the stereo field during denoising.
That depends on the operation, the selected model, and your audio input length. Usually, it's about 30s. Large models on long audio can take up to 5mn. You can leave the page and come back later.
Click the Export button, then choose Download all current stems.
This downloads the stems currently visible in your project, using whatever version is selected for each stem. For example, if your vocal stem is set to a restored version and your bass stem is set to the original version, the export will include those current versions.
To change what gets exported, first select the version you want on each stem waveform, then click Export again.
Ready to Remove SFX from TV Show Audio?
Keep the music, isolate the noise, and recover cleaner soundtrack layers from old mixed recordings.