post/upscale-audio

Restore low-quality audio and export a cleaner WAV

Send a compressed song, damaged recording, voice track, or stem. Choose what needs fixing. Your app or agent gets a restored WAV that is ready for editing, mastering, or download.

Get an API key View examples

How this endpoint works

Use this API when users need to upscale MP3 to WAV, restore missing high frequencies, fix compressed AI music, clean speech, remove clipping, reduce reverb, or repair a stem. Unlike file conversion, restoration predicts missing audio content. Choose Apollo, AudioSR, UniverSR, or a problem-specific preset after you know what the source needs.

1
Choose the audio and problem
Send the track or stem ID and choose the restoration preset that matches the damage.
2
Wait for restoration
Save id and poll the restoration job until it finishes or fails.
3
Download the restored WAV
Download the cleaner file or send it directly to mastering or stem separation.

Common use cases

Choose this operation when it matches the source and result your workflow needs.

Upscale MP3 to WAV

Rebuild missing high frequencies and reduce MP3 compression artifacts before editing or mastering.

Fix hiss, clipping, or reverb

Choose a problem-specific preset for a noisy AI song, clipped recording, reverberant vocal, or damaged stem.

Restore voice recordings

Improve low-bandwidth speech, vocals, podcasts, phone calls, or voice notes before publishing.

Processing used by 60,000+ music makers

Results people rely on

“I've been loving the app. The audio restoration works amazing on my suno songs”

Jordi

Audio Super Resolution

“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.”

Dan Campbell ~Riffster

“Love it! Makes everything crisp!”

The Grim Tower

“Sensacional”

Francisco

Hear audio restoration results

These shared user results demonstrate the restoration output available through the same processing system.

More User Examples

Choose what you want to fix

MP3 Music Restoration (Apollo, 2025)

preset="universal_enhancer"

Repairs MP3 compression damage and restores missing high frequencies. Trained on high-quality music paired with degraded MP3 versions. Output sample rate matches the prepared input rate (44.1kHz or 48kHz). Recommended for: online source imports, songs downloaded from the internet, compressed sound, tracks missing >16Khz. Not effective to regenerate 16Khz+ audio? Try AudioSR instead.

Parameters

stereo_modeStereo Modestring

Controls how stereo material is processed. Defaults to mid_sides, which processes center and side content separately; left_right processes channels independently, mono folds to mono, and sides_only/mid_only process one component while preserving the other. Supported by universal_enhancer, apollo_voice, universr, reuse, flashsr, audiosr, novasr, dacvae, and lavasr. Other presets ignore this field.

Allowed values

mid_sidesStereo (Mid/Sides)DefaultRecommended
sides_onlySides onlyProcess the sides and keep the original center.
mid_onlyMid onlyProcess the center and keep the original sides.
left_rightStereo (L/R)
monoMono

Neural Remix - Stable Audio 3 (Stable Audio 3 Medium, 2026)

preset="stable_audio_3"

Remixes instrumentals from audio and a text prompt. This prompt-guided remix mode uses the source audio as a reference while the text prompt steers style, tone, and instrumentation. Recommended for: instrumental only (no vocals!), creative remixes, inpainting missing musical ideas, turning noisy frequencies into music, and low-end or texture repair.

Parameters

model_nameModel variantstring | null

Selects the model variant used inside the restoration preset. Supported by dereverb, dialogue_isolate, denoise, universr, acestep_15_xl, and stable_audio_3. UniverSR variants support audio/vocal super-resolution, and ACE-Step/Stable Audio variants support prompt-guided remastering. Other presets choose their model from preset and ignore this field.

Allowed values

stable-audio-3-mediumStable Audio 3 MediumRecommended

strengthRemix Strengthnumber

How much Stable Audio 3 can reinterpret the source. Higher values let the model rewrite more of the original recording.

Common values

0.01Minimal edit
0.1Light edit
0.3Bit more edit
0.5Balanced editRecommended
0.6Moderate remix
0.7Strong remix
0.95Totally different songDefault

promptPromptstring

Describe the target sound, style, instrumentation, tempo, and production character Stable Audio 3 should create from the source audio.

Default"high quality studio recording CD quality"

Example

"clean studio master, full bandwidth, natural transients"

prompt_strengthPrompt Strengthnumber

How strongly Stable Audio 3 follows the text prompt. Higher values amplify prompt guidance relative to the reference audio.

Range: 0 to 10

Common values

0.5Less prompt strengthKeeps the prompt influence light so the source audio remains the main guide.
1Base prompt strengthDefaultRecommendedUses the normal Stable Audio 3 prompt conditioning strength.
2More promptMakes the prompt easier for the model to follow while still leaving room for the reference audio.
3Stronger promptPushes the result further toward the prompt while retaining some reference influence.
4Even more promptPushes the result harder toward the described style, instruments, or production character.
5High prompt strengthPrioritizes the described style and production character over the reference audio.
6Very high prompt strengthStrongly prioritizes the prompt with limited faithfulness to the reference audio.
7Maximum promptStrongly prioritizes the prompt and can make the result less faithful to the reference audio.

inpaint_regionsInpaint regionsArray<{ start: number; end: number }> | null

Lists source time ranges to regenerate while preserving the rest of the input audio. Each range requires start and end times in seconds. Supported by stable_audio_3 only; other presets ignore this field. Omit it to run an ordinary audio-to-audio remix.

Example

[{"end":8,"start":4}]

Neural Remix - ACEStep 1.5 XL (ACE-Step 1.5 XL, 2026)

preset="acestep_15_xl"

Recreates music in remix mode, similar to SUNO 'cover' mode. It uses similar sounds to the reference, but adds new notes if you lower the reference strength. Recommended for: Bass tracks, inpainting missing notes in stems, low end mudiness. Interesting results when blended with the original audio.

Parameters

model_nameModelstring | null

Allowed values

acestep-v15-xl-turboAceSTEP turbo
acestep-v15-xl-sftAceSTEP SFT

strengthOriginal Influencenumber

How much the original audio influences the result. 1.0 means the model tries to match the original as close as possible. 0.1 means it's a loose reference.

Common values

1.0As close as possible
0.99Almost original
0.5Inspiration
0.1Creative interpretation

promptPromptstring

AceSTEP XL is a 2026 music generation model similar to SUNO. This prompt is passed to the model to influence the result. ACE Step authors mention that it's best if it describes the original track: style, instruments, tempo, key.

Default"high quality studio recording CD quality"

Example

"clean studio master, full bandwidth, natural transients"

AudioSR Upscaler (Audio SR, 2022)

preset="audiosr"

Regenerates high frequencies above the selected cutoff while keeping lower frequencies from the original audio. Recommended for: Low quality recordings, missing high frequencies, hissing noise around 10Khz (hihats, voice, suno hiss). Low thresholds (eg: 3Khz) will change audio the most, while high threshold will mostly preserve what's already here. Not recommended for: Bass tracks, muddy low end. Use Neural Remix instead.

Parameters

frequency_cutoffStrengthinteger

Sets where AudioSR starts regenerating high frequencies. Lower cutoffs regenerate more of the track for a stronger effect; higher cutoffs focus on the top end for a subtler, more nuanced result.

Allowed values

16000Very Subtle (16 kHz cutoff)
13000Subtle (13 kHz cutoff)Default
10000Mild (10 kHz cutoff)
8000Medium (8 kHz cutoff)Recommended
5000Pronounced (5 kHz cutoff)
4000Strong (4 kHz cutoff)
3000Very Strong (3 kHz cutoff)

reconstruction_methodReconstructionstring

Controls how generated high frequencies are combined with the source audio. Supported by audiosr and universr. For AudioSR, multiband_ensemble low-passes the original audio at frequency_cutoff minus 1000 Hz, high-passes the AudioSR output at the same crossover, then sums both bands. original_signal uses frequency_cutoff as a hard final spectrum boundary: original source bins below the cutoff and generated bins at or above it. For UniverSR, original preserves the legacy reconstruction path, while original_signal keeps the bandwidth-limited input for model conditioning but takes the final low-frequency bins from the original 48 kHz source signal. Other presets ignore this field.

Allowed values

multiband_ensembleMultiband EnsembleRecommendedBlends the original low frequencies with restored high frequencies for a gradual transition.
original_signalSeamless ReconstructionKeeps your original audio below the selected cutoff and restores only the higher frequencies.

stereo_modeChannelsstring

Allowed values

mid_sidesStereo (Mid/Sides)DefaultRecommended
sides_onlySides onlyProcess the sides and keep the original center.
mid_onlyMid onlyProcess the center and keep the original sides.
left_rightStereo (L/R)
monoMono

UniverSR Upscaler (UniverSR, 2026)

preset="universr"

Upscale music, voice, and sound effects. UniverSR is a 2026 model developed by the University of Seoul which performs audio super-resolution directly in the complex STFT domain using flow matching. Very similar to AudioSR, but with more coherent high ends. Recommended for: Low quality recordings, missing high frequencies, hissing noise around 10Khz (hihats, voice, suno hiss). Low thresholds (eg: 4Khz) will change audio the most, while high threshold will preserve what's already here. Not recommended for: muddy bass or muddy low end. Use Neural Remix instead.

Parameters

model_nameModelstring | null

Allowed values

universr-audioOriginalRecommended
universr-audio-finetune-v1Fine-tune v1

frequency_cutoffStrengthinteger

Sets the upper frequency boundary in hertz where a bandwidth-extension model starts rebuilding audio. Supported by audiosr and universr. AudioSR accepts 3000, 4000, 5000, 8000, 10000, 13000, or 16000. UniverSR accepts 4000, 6000, 8000, or 12000. Other presets ignore this field.

Allowed values

12000Subtle (12 kHz cutoff)
8000Medium (8 kHz cutoff)Recommended
6000Pronounced (6 kHz cutoff)
4000Strong (4 kHz cutoff)

stereo_modeChannelsstring

Allowed values

mid_sidesStereo (Mid/Sides)DefaultRecommended
sides_onlySides onlyProcess the sides and keep the original center.
mid_onlyMid onlyProcess the center and keep the original sides.
left_rightStereo (L/R)
monoMono

reconstruction_methodReconstructionstring

Allowed values

original_signalSeamless ReconstructionKeeps the original 48 kHz low-frequency bins in the final spectrum while still using the cutoff signal for model conditioning. This usually avoids a visible crossover seam because the low band keeps the source frequency profile.
originalOriginal ReconstructionDefaultRecommendedLegacy UniverSR assembly. The final low band comes from the downsampled and upsampled cutoff signal, whose resampling rolloff can dip energy near the cutoff and leave a seam where generated highs begin.

NovaSR Speech Upscaler (NovaSR, 2026)

preset="novasr"

Upscaling model trained on English speech. Best for restoring podcasts, voice-overs, or isolated vocal tracks.

Parameters

stereo_modeChannelsstring

Allowed values

mid_sidesStereo (Mid/Sides)DefaultRecommended
sides_onlySides onlyProcess the sides and keep the original center.
mid_onlyMid onlyProcess the center and keep the original sides.
left_rightStereo (L/R)
monoMono

FlashSR Upscaler (FlashSR, Jan 2025)

preset="flashsr"

Restores missing high frequencies and detail in one fast pass. Recommended for: Western music, single instrument upscaling, preparing 44.1Khz stems before Atmos Export. Not recommended for: Bass.

Parameters

stereo_modeStereo Modestring

Allowed values

mid_sidesStereo (Mid/Sides)DefaultRecommended
sides_onlySides onlyProcess the sides and keep the original center.
mid_onlyMid onlyProcess the center and keep the original sides.
left_rightStereo (L/R)
monoMono

Remove speed variation (make bpm constant) (Beat This!, 2024)

preset="constant_bpm"

Fixes wonky tempo in music generated by SUNO when the speed keeps changing throughout the song. Recommended for: SUNO songs that should stay at a constant BPM and align cleanly to a beat grid. It can also help tighten tempo variations in live performances.

Neural Reconstruction (DACVAE, 2024)

preset="dacvae"

Rebuilds all frequencies through a neural codec to reduce unnatural frequency patterns. Recommended for: weird hihats sounds in electronic music.

Parameters

stereo_modeChannelsstring

Allowed values

mid_sidesStereo (Mid/Sides)DefaultRecommended
sides_onlySides onlyProcess the sides and keep the original center.
mid_onlyMid onlyProcess the center and keep the original sides.
left_rightStereo (L/R)
monoMono

Remove Clipping

preset="declip"

Fixes harsh crackling when volume is too high. Algorithms find optimal settings to remove all crackling, while still maintaining loudness.

Remove Noise

preset="denoise"

Reduces hiss, hum, background noise, and optional source bleed while keeping the main vocals/instruments. Uses the same model family as stem splitting, but returns a single cleaned track only.

Parameters

model_nameModel Variantstring | null

Allowed values

denoiseDenoiseRecommended
denoise_debleedDenoise and debleed

Remove Reverb

preset="dereverb"

Choose Long Reverb (strong) for long reverb tails in singing, music, and live recordings. Choose Room echo (light) for subtle room echo in podcasts, voice-overs, and dialogue.

Parameters

model_nameModelstring | null

Allowed values

dereverbLong Reverb (strong)Recommended
dialogue_isolateRoom echo (light)

Remove Crowd Noise

preset="decrowd"

Removes audience noise from live recordings while preserving the performance. Uses the same model family as stem splitting, but returns a single cleaned track only.

Keep Only Center Mono (Center Wide v3, 2026)

preset="phantom_center"

Extracts the "phantom center", the content that should be mono in a track. Use this for: bass, kick drums, podcast voice. Removes phaser, chorus, or flanger from instrument stems. Good for mixing.

RE-USE Speech Enhancer (NVIDIA RE-USE, 2026)

preset="reuse"

Improve clarity, upscale, remove reverb, remove noise and audio glitches in multilingual speech. Recommended for: getting dry vocals, clearer podcasts, noisy voice notes, etc. Not recommended for: full music mixes or instrumental upscaling. Use UniverSR, AudioSR, or a music restoration model instead.

Parameters

stereo_modeChannelsstring

Allowed values

mid_sidesStereo (Mid/Sides)DefaultRecommended
sides_onlySides onlyProcess the sides and keep the original center.
mid_onlyMid onlyProcess the center and keep the original sides.
left_rightStereo (L/R)
monoMono

Singing Upscaler (Apollo Voice, 2025)

preset="apollo_voice"

Specialized voice upscaling. Restores missing high frequencies and removes compression artifacts in lower frequencies. Output sample rate is 44.1kHz for lower-rate inputs and 48kHz for 48kHz+ inputs.

Parameters

stereo_modeStereo Modestring

Allowed values

mid_sidesStereo (Mid/Sides)DefaultRecommended
sides_onlySides onlyProcess the sides and keep the original center.
mid_onlyMid onlyProcess the center and keep the original sides.
left_rightStereo (L/R)
monoMono

Code examples

Server-side example

JavaScript (Node.js)

import { writeFile } from "node:fs/promises";

const API_URL = "https://api.neuralanalog.com";
const API_KEY = process.env.NEURALANALOG_API_KEY;

async function waitForCompletion(objectType, objectId) {
  while (true) {
    const response = await fetch(`${API_URL}/status/${objectType}/${objectId}`, {
      headers: { "X-API-Key": API_KEY },
    });
    if (!response.ok) {
      throw new Error(`Status check failed with ${response.status}`);
    }

    const status = await response.json();
    if (status.is_failed) {
      throw new Error(status.error_message || `${objectType} processing failed`);
    }
    if (status.is_complete) {
      return status;
    }
    await new Promise((resolve) => setTimeout(resolve, 5000));
  }
}

const requestResponse = await fetch(`${API_URL}/upscale-audio`, {
  method: "POST",
  headers: {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "audio_id": "6c62f8e7-02a3-48c0-a5b5-5de87ed9c31a",
  "preset": "universal_enhancer",
  "bit_depth": 24
}),
});
if (!requestResponse.ok) {
  throw new Error(`Restoration request failed with ${requestResponse.status}`);
}

const result = await requestResponse.json();
const jobId = result["id"];
const status = await waitForCompletion("upscaled", jobId);

const downloadResponse = await fetch(
  `${API_URL}/download/upscaled/${jobId}`,
  { headers: { "X-API-Key": API_KEY }, redirect: "follow" },
);
if (!downloadResponse.ok) {
  throw new Error(`Download failed with ${downloadResponse.status}`);
}
await writeFile("restored.wav", Buffer.from(await downloadResponse.arrayBuffer()));

Parameters

Send the API key from a trusted server. Never expose it in client-side JavaScript.

JSON request body

audio_id

requiredstring

Identifies the full audio file to restore.

Example: "6c62f8e7-02a3-48c0-a5b5-5de87ed9c31a"

preset

optionalstring

Selects the restoration model or repair process to run. Each preset supports its own parameters; fields that do not apply to the selected preset are ignored.

"universal_enhancer""constant_bpm""novasr""flashsr""dacvae""declip""dialogue_isolate""denoise""dereverb""decrowd""phantom_center""audiosr""apollo_voice""lavasr""reuse""acestep_15_xl""stable_audio_3""universr"

Default: "universal_enhancer"

stereo_mode

optionalstring

"mid_sides""left_right""mono""sides_only""mid_only"

Default: "mid_sides"

frequency_cutoff

optionalinteger

Default: 13000

model_name

optionalstring | null

"dereverb""dialogue_isolate""denoise""denoise_debleed""universr-audio""universr-audio-finetune-v1""universr-vocal""acestep-v15-xl-turbo""acestep-v15-xl-sft""stable-audio-3-medium"

reconstruction_method

optionalstring

"multiband_ensemble""original""original_signal"

Default: "original"

strength

optionalnumber

Controls processing intensity from subtle cleanup to aggressive restoration. Higher values preserve less of the degraded source. Supported by acestep_15_xl and stable_audio_3. Other presets ignore this field.

Default: 0.95

prompt

optionalstring

Describes the sound that a prompt-guided model should create from the source audio. Supported by acestep_15_xl and stable_audio_3. Other presets ignore this field. Keep the prompt under 256 characters.

Default: "high quality studio recording CD quality"

Example: "clean studio master, full bandwidth, natural transients"

prompt_strength

optionalnumber

Controls how strongly Stable Audio 3 follows prompt relative to the reference audio. Higher values give the prompt more influence. Supported by stable_audio_3 only; other presets ignore this field. Accepts values from 0 to 10.

Default: 1

inpaint_regions

optionalarray<object> | null

Example: [{"end":8,"start":4}]

stem_id

optionalstring | null

Selects one stem from the parent audio as the restoration source. Omit it to restore the full audio file.

Example: "abf8a992-1c4e-4935-93f0-197116e77e49"

source_upscaled_id

optionalstring | null

Selects an existing restored version as the source for another pass.

Example: "d66cf940-bf26-45bb-80f7-332f26b6859a"

source_mastered_id

optionalstring | null

Selects an existing mastered artifact as the restoration source.

Example: "f5db8e4b-2e74-4198-a8de-0c3a398620e9"

source_temporary_mix_key

optionalstring | null

Short-lived Current Main Mix or Current All Stems Mix R2 source key.

selection

optionalobject | null

Limits restoration to a start and end time in seconds. Omit it to restore the full selected source.

Example: {"end":42,"start":12.5}

bit_depth

optionalinteger

Output WAV bit depth for the restored audio.

1624

Default: 24

hq_streaming_format

optionalstring

Selects the compressed format generated for browser playback and streaming alongside the restored WAV output.

"aac""mp3""flac"

Default: "aac"

Successful response

200Successful Response

id

requiredstring

ID of the queued restored audio version.

Example: "d66cf940-bf26-45bb-80f7-332f26b6859a"

status

requiredstring

Queueing status for the restoration job.

Example: "processing"

message

requiredstring

Human-readable queueing result.

Example: "Audio restoration queued"

Errors

A missing or invalid X-API-Key returns an authentication error. Validation errors use the declared 422 response below.

422Validation Error

detail

optionalarray<object>

No description provided.

Next steps

poll Download Master the restored audio Try audio restoration Read the restoration guide

How this endpoint works

Choose the audio and problem

Wait for restoration

Download the restored WAV

Common use cases

Upscale MP3 to WAV

Fix hiss, clipping, or reverb

Restore voice recordings

Results people rely on

Hear audio restoration results

Choose what you want to fix

MP3 Music Restoration (Apollo, 2025)

Neural Remix - Stable Audio 3 (Stable Audio 3 Medium, 2026)

Neural Remix - ACEStep 1.5 XL (ACE-Step 1.5 XL, 2026)

AudioSR Upscaler (Audio SR, 2022)

UniverSR Upscaler (UniverSR, 2026)

NovaSR Speech Upscaler (NovaSR, 2026)

FlashSR Upscaler (FlashSR, Jan 2025)

Remove speed variation (make bpm constant) (Beat This!, 2024)

Neural Reconstruction (DACVAE, 2024)

Remove Clipping

Remove Noise

Remove Reverb

Remove Crowd Noise

Keep Only Center Mono (Center Wide v3, 2026)

RE-USE Speech Enhancer (NVIDIA RE-USE, 2026)

Singing Upscaler (Apollo Voice, 2025)

Code examples

Server-side example

Parameters

JSON request body

Successful response

Errors

Next steps