Help & FAQ

The Refiner takes any audio file and produces a cleaner, higher-fidelity version of it. Works on AI-generated tracks from Suno or Udio, but also on podcasts, voice memos, demos, old mp3s, live recordings — anything that was compressed or is missing detail. The typical workflow is:

New verified accounts start with 5 welcome credits and 30 days of Pro feature access. After that, the account uses its normal plan.

1. If you already have an invitation, sign in at /sign-in. Otherwise, join the waitlist for access.
2. Drop a track into the dashboard. MP3, WAV, or FLAC, up to 8 minutes long.
3. Pick Enhanced, the recommended default. Flow Matching remains visible but is temporarily unavailable while we review output quality. Optionally flip on AI artifact removal and Finalize to try the recommended complete workflow. Both are included during the welcome trial and on Hobby, Pro, and Studio afterward. You get a free 10-second reference preview before Finalize runs. It auditions only the reference match; with Reference Off it plays the original excerpt.
4. Wait for the job to finish, then download the refined WAV.

Need isolated stems instead of a refined mix? Head to the Stems page for vocals / drums / bass / other or speech / background splits. See the stem separation section below for details.

Preparing an EP or album? Use the Albums page to give every track one processing profile and level-match the finished masters as a complete release. See the album mastering instructions below.

The Refiner ships two families of models. They take very different paths to the same destination, and their trade-offs are worth understanding before you spend credits.

Enhanced — neural audio reconstruction

Enhanced uses a trained audio model and GPU processing to synthesize high-frequency detail from your recording. It goes beyond an EQ lift or a noise filter: the model constructs a plausible restored version, aiming for more definition and air. It cannot know the exact detail that was lost, and its reconstruction can change texture and timbre.

Enhanced is our recommended starting point and costs 1 credit. Its processing path is shorter than Flow Matching, but it is still model inference, not a lightweight filter. End-to-end time varies with track length, queue demand, and worker startup. Compare the result with the original at matched listening levels; generated detail is not always preferable on every source.

Flow Matching — compute-intensive iterative reconstruction

Temporarily unavailable. Flow Matching is paused for new jobs while we review output quality. Its card remains visible but disabled in the app. Use Enhanced for now; existing results and downloads are unaffected.

Flow Matching uses a different generative restoration approach, guided by your source audio. It rebuilds detail through repeated refinement rather than a simple filtering pass. This is intensive GPU computation, and it can reshape fine texture, transients and ambience—not just reduce noise.

Normal and High use different processing depths, with High requiring more compute. That produces an alternative reconstruction, not a guaranteed quality upgrade or an exact recovery of the original master. Before the pause, Normal cost 3 credits and High cost 4. Enabling AI artifact removal added a cleaning stage first. Neither preset is designed or guaranteed to change AI-detector results.

AI Artifacts — standalone cleaning

The AI-artifact cleaner running on its own, with no refinement model after it. Source separation plus per-stem DSP strips the residue AI generators leave behind — subtle haze, unnatural peaks, generation noise — so you get a noticeably cleaner version of the same track. It costs 2 credits and adds a cleaning stage that can take roughly the track's length, plus queue and worker startup time. It is available on Hobby, Pro, and Studio.

Vocal De-mush & Vocal Restore — vocal and voice cleanup

Vocal De-mush (1 credit) cleans AI-generated vocal stems and reduces background noise in podcasts and spoken-word recordings. Upload a voice recording directly; for a full song, separate the vocal on the Stems page first. Vocal Restore (2 credits) adds an Enhanced restoration pass after vocal cleanup to rebuild detail in singing vocal stems. Both are available on Pro and Studio.

Vocal De-mush runs AI artifact cleanup first, then blends in vocal restoration. The Restoration strength fader starts at 25%; lower it to retain more soft word endings and breaths, or raise it for more restoration. At 0%, you hear the cleaned vocal alone. More of the original noise may remain at lower amounts. The result is a centered mono voice, even when the uploaded file has two channels.

Finalize — automated mastering

Finalize is not a refinement model — it's a DSP mastering chain that runs after everything else. It analyzes the finished audio and applies corrective EQ, glue compression, and harmonic saturation from a two-character analog model — a valve-triode shaper for even harmonics and a transformer shaper for odd harmonics, dosed mid/side so the center gains density without narrowing the image — plus stereo polish (phase-correlation repair, a mono fold below ~150 Hz so the low end holds up on club PAs and phones, and a touch of high-frequency side air for width), then brings the track to its release target — −9 LUFS by default — under a −1 dBTP true-peak ceiling. It adds a final processing stage whose duration varies with the track and worker state.

The knobs: strength (Gentle, Medium, Strong), loudness target (−9 LUFS by default; −7, −14, or −16), and harmonics (Off, Standard, Hot), plus optional reference matching — upload a reference track, or pick a preset (10 curated factory presets plus any you save). After upload there's a Finalize setup step with a free 10-second reference preview. It auditions only the selected reference's tonal shape; with Reference Off it plays the original excerpt. Strength, loudness, and harmonics are applied to the final master and are not rendered in this preview.

Two ways to use it: flip the Finalize (mastering) toggle on Enhanced (Hobby, Pro, and Studio; no extra credits) — or pick the standalone Finalizepreset to master a track that's already mixed (1 credit). On those refinement jobs the mastered version is the default download and the pre-master stays available as a second file; standalone delivers the mastered file, and your upload is the pre-master. It's deliberately conservative: it won't replace a mastering engineer, but it closes most of the gap between a raw AI export and a released track.

Output format

All presets output WAV. Sample rate is 44.1 kHz by default (48 kHz on Pro and Studio — better for video work and some mastering pipelines). Bit depth is 24-bit. A 32-bit float option normally belongs to Flow Matching on Pro and Studio. That option is temporarily unavailable with the paused preset.

Which to pick

Default to Enhanced for most material — it is fast, inexpensive, and our recommended starting point. Flow Matching is paused while we review output quality, so it cannot be selected for new work. Finalize can master an Enhanced result — that is the difference between a clean file and a release-loud one.

Rebalance is an optional pause inside an Enhanced refinement with AI artifact removal enabled. It is available on Pro and Studio with no extra credit beyond the processing already selected. With Rebalance off, the normal refinement runs straight through without pausing for a stem mix.

1. Turn on AI artifact removal and Rebalance stems

The cleaner prepares temporary vocals, drums, bass, and other stems, then pauses before rebuilding the track. Rebalance is not the Stems page: it does not produce separate downloadable stem files. The Rebalance switch starts off for every new submission and is not remembered; turn it on deliberately for each batch you want to pause.

2. Audition the mix and set relative levels

Preview the four cleaned stems together and move each level fader independently. A positive gain brings that stem forward; output protection may manage the combined peak level to preserve headroom. The preview is an audition of the current controls, not a finished downloadable render. Because the browser uses encoded audition files while the server renders from lossless stem checkpoints, the final level and dynamics can differ slightly. When selected, Humanizer processes the rebalanced mix next, and Finalize runs last. Those stages are not included in this preview.

3. Add and shape vocal reverb if needed

Curated convolution reverb is available on the vocal only. Low cut removes low frequencies from the wet reverb return, while High cut softens its upper frequencies. Both filters affect the reverb return; the dry vocal stays unchanged.

4. Render the final mix

Choose Render final mix to apply the settings and resume processing. Humanizer, when selected, processes the rebalanced mix first; Finalize, when selected, runs last. Working stems and audition previews remain private and are deleted after final rendering; source and finished files remain available for the normal 7-day retention period.

If you close the mixer before rendering, the job remains paused at Rebalance ready. Open it again from the refinement on your dashboard when you are ready to continue.

For a fuller walkthrough, see How to rebalance cleaned stems before the final mix.

Albums is the release-level workflow for an EP or full album. Instead of configuring and mastering tracks one at a time, you create an album folder with one locked processing profile. Every track then uses the same refinement model, cleanup and Humanizer choices, mastering strength, harmonics, loudness target, sample rate, and output format. Albums is available on Pro and Studio plans. The final perceptual balance pass is included in the workflow.

1. Create the album folder

Open the Albums page, choose New album, and enter the release title and artist. Pick Enhanced + Finalize or Finalize only, then set the loudness, strength, harmonics, and output format. The Flow Matching option remains visible but disabled while the preset is paused. Enhanced profiles can apply AI cleanup; Humanizer's Stereo resynthesis is off by default. Enable it if you want mix resynthesis, which may widen the stereo image. Finalize only skips both cleanup and Humanizer. Check the profile carefully: it is locked when the folder is created so every track stays coherent.

2. Add tracks in final album order

Drop several MP3, WAV, or FLAC files onto the album, or use Add album tracks. Multiple files are queued in the order you add them, so arrange the selection in the intended album sequence first. The balance pass requires at least two completed tracks, and a folder can hold up to 100. Each track uses the ordinary credit cost of the processing profile you chose.

Wait until each file has been accepted and its job has started before closing the tab. After that, refinement and mastering continue in the backend — you can visit another page, close the browser, and return to the album folder later. If an upload fails, retry the same file to replace that failed position, or remove the failed track and add it again.

3. Lock and balance the release

When at least two tracks have completed and every individual master is ready, choose Lock & balance album. This freezes the track list. The Refiner analyzes the mastered songs together, chooses a robust shared perceptual loudness anchor that respects the release target, and renders a true-peak-safe delivery master for each track. This final balance pass is included — it does not reserve another credit.

The matched versions become the album downloads only when every track succeeds, so a partial balance can never replace part of the release. The individual pre-balance masters remain preserved. If balancing fails, use Retry balance; you can also remove a problem track before retrying.

4. Download the finished album

When the folder says Album balance complete, use Download album ZIP. The ZIP contains the perceptually level-matched masters in album order, ready to move into your release folder or distributor workflow.

The Refiner can also split a track into isolated stems — useful for remixing, dropping the instrumental into a DAW, building a karaoke version, isolating a vocal to use elsewhere, or pulling speech out of a podcast for transcription. Stem separation is a Pro feature; Free users get one lifetime trial split.

Open the Stems page from the dashboard, drop a track, and pick one of three engines. Output is one WAV per stem plus a single ZIP containing all of them — handy for one-click download.

Demucs — fast 4-stem classic

The original go-to source-separation model. Splits the track into vocals, drums, bass, and “other” (everything else). Fast, well-tested, and the right default for most music.

Melband — newer transformer

Mel-Band RoFormer is a more recent architecture that produces cleaner separations — less bleed between stems and tighter isolation on vocals and percussion in particular. The trade-off is runtime: it takes longer than Demucs. Reach for it when stem quality matters more than speed (final remix, sampling, lifting a vocal you actually plan to use prominently).

Voice Cleanup — speech vs. background

A 2-stem split optimized for spoken-word audio: speech on one stem, everything else (music, room noise, applause) on the other. Useful for podcast editing, lifting an interview voice out of a noisy recording, or preparing speech-only audio for transcription.

Cost and limits

Each split costs 3 credits regardless of which engine you pick. Track length limit is the same as refinement (8 minutes). After the split completes you can preview every stem in the in-app multitrack player before downloading, and the convenience ZIP stays available alongside the individual WAVs.

Refinements are paid for with credits. New verified accounts receive 5 welcome credits and 30 days of Pro feature access. After that, Free provides 2 credits per month for Enhanced. Paid subscriptions (Hobby, Pro, Studio) add monthly credits and plan features.

Monthly subscription credits reset at the end of each billing cycle and do not roll over. Credit-pack credits do not expire and stack on top of subscription credits. A Credit Pack adds balance only: it does not change the account's plan, extend the welcome trial, or unlock features outside that plan.

If a refinement comes out worse than the source, email support@therefiner.app with the job ID (visible in the dashboard). We'll review the result and refund the credits when appropriate.

Pricing details and plan comparisons are on the pricing page.

Manage your plan, payment method, and credit balance from Account → Billing. Cancel any time — your subscription remains active until the end of the current billing period.

Source files and refined outputs stay in your private workspace for 7 days after refinement so you can preview or re-download them. After 7 days the files are deleted, while the job record remains in your history. Temporary Rebalance working stems and audition previews are deleted after final rendering. We never use your audio to train models.

To remove a finished result sooner, choose Delete beside it on the dashboard and confirm. This removes its job record, uploaded audio and reference files, processed versions, previews and any stem splits created from it. Separate reruns keep their own files. Active or paused processing must finish first. Deletion cannot be undone and does not refund credits; your credit history is retained. If file cleanup is interrupted, use Retry delete to finish.

Upload fails: check the file is in a supported format (MP3, WAV, or FLAC) and under 8 minutes long. Tracks longer than 8 minutes are rejected at upload — split them and refine in chunks.

Job appears stuck: refresh the dashboard once to load the latest server state. If the status still does not change, email support with the job ID. Do not start repeated copies of the same job; failed jobs automatically return their reserved credits.

Result sounds wrong: start with Enhanced and compare one setting at a time. Try AI artifact removal with Humanizer, then add Finalize; audition Reference Off before matching another track. Extreme inputs such as very short clips or unusual instruments can still vary. Email support with the job ID if the result remains off — we read every report.

Email support@therefiner.app with the job ID (if relevant) and a short description. We typically respond within one business day.