Clear.
On-device speech enhancement that gives your recording the warm, close-miked sound of a podcast studio, processed 100% on-device.
Demo
Studio sound, no cloud bill.
Adobe Podcast, Dolby and Auphonic bill by the minute and require audio or video to be uploaded to their servers. Clear runs a 5-minute clip in 1s on an iPhone 16 Pro, on the device.
Record on a laptop or phone mic in an untreated room with traffic outside, and the result sounds close-miked: warm low-mids, the voice forward, no background noise. With output presets for Spotify, Apple Podcasts, and YouTube loudness.
Clear is available in two variants: clear-studio and clear-natural. Studio, the default, cleans down to near silence. Natural keeps room tone, breath and lip texture for treated rooms and intentional voiceover.
5 minutes of audio in 1s.
302x realtime on an iPhone 16 Pro and 345x on a MacBook Pro M5: enhance, master, and re-encode a 60-second clip, best of three, on the device.
clear-studio, enhance, master, and re-encode on a 60-second clip, best of three
| Device | Realtime factor |
|---|---|
| iPhone 16 Pro | 302x |
| MacBook Pro (M5) | 345x |
Internal measurements on the shipped Core ML build: a 5-minute mono clip through enhancement, mastering, and re-encode, iOS 27.0. The model card reports 302x on an iPhone 16 Pro and 345x on a MacBook Pro (M5) for a 60-second clip, best of three. Speed on Android and in the browser is not measured yet, and we have not published an audio-quality score against the cloud tools.
Rescue a recording from a bad room.
Podcast and video mastering
Clean a laptop-mic or untreated-room recording in one pass. Pick Apple Podcasts, Spotify, YouTube, or EBU R128, and Clear automatically normalizes the volume to their specification.
Kill the room, not only the hiss
Most denoisers stop at the hiss. Clear removes the reflections too, so a podcast, video or meeting recorded at home or in a conference room sounds close-miked instead of boxy.
No upload, no per-minute bill
Studio cleanup as a feature has no metered pricing for users. Enhancement runs on-device, so there is no cloud audio bill that grows with every minute of audio processing.
Fix an hour-long recording on a phone
The file path streams chunk by chunk when writing to disk, so a one-hour recording uses the same memory as a ten-second clip. The enhanced file lands next to the original.
Inspiration
Ideas to build with Clear. Copy a prompt into your coding agent and go.
Add a one-tap 'clean audio' button that removes noise and room echo.
Add a 'clean audio' action that runs Desert Ant's Clear on-device to remove background noise and room reverb from a recording, with presets for podcast, video, and voiceover loudness. Nothing uploaded. Build it with the Desert Ant SDK. Clear (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/clear/. Install: SwiftPM desert-ant-core; Maven ai.desertant:clear:3.1.0; npm i @desert-ant-labs/clear @litertjs/core # browser. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Master a podcast episode to platform loudness, on the device.
Build a podcast export step that runs Desert Ant's Clear to enhance and master the episode to Apple Podcasts / Spotify / YouTube loudness locally, so it's ready to publish without a cloud mastering service. Build it with the Desert Ant SDK. Clear (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/clear/. Install: SwiftPM desert-ant-core; Maven ai.desertant:clear:3.1.0; npm i @desert-ant-labs/clear @litertjs/core # browser. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Rescue a recording made in a noisy, untreated room.
Build a 'rescue this recording' feature: run Desert Ant's Clear on-device to make a take recorded in a kitchen or hotel room sound close-miked, warm, and free of background noise. Build it with the Desert Ant SDK. Clear (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/clear/. Install: SwiftPM desert-ant-core; Maven ai.desertant:clear:3.1.0; npm i @desert-ant-labs/clear @litertjs/core # browser. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Clean the audio on a phone video in one pass.
In a video app, add a step that runs Desert Ant's Clear over the audio track of a phone video to remove wind, hiss, and echo before sharing. On-device, no per-minute cost. Build it with the Desert Ant SDK. Clear (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/clear/. Install: SwiftPM desert-ant-core; Maven ai.desertant:clear:3.1.0; npm i @desert-ant-labs/clear @litertjs/core # browser. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Record, clean, transcribe, and clip: a whole creator pipeline, offline.
Build a creator pipeline: Desert Ant's Clear cleans the recording, Voz transcribes it, and Clips pulls the shorts, all on the device so a full episode never touches a server. Build it with the Desert Ant SDK. Clear (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/clear/. Voz (Swift). Install and API: https://desertant.com/docs/voz/. Clips (Swift). Install and API: https://desertant.com/docs/clips/. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
Build a voice-notes app that cleans the audio and transcribes it offline.
Build a voice-notes app. Run Desert Ant's Clear on the recording for studio-clean audio, then Voz to transcribe it with word timestamps, entirely on-device so a note taken in a noisy room still reads well and never leaves the phone. Build it with the Desert Ant SDK. Clear (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/clear/. Voz (Swift). Install and API: https://desertant.com/docs/voz/. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
A clean, filler-free transcript from a raw, noisy recording.
Build a transcript pipeline: Desert Ant's Clear cleans the audio, Voz transcribes it, and Uhm removes the fillers, so a messy recording becomes a clean transcript, on-device. Build it with the Desert Ant SDK. Clear (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/clear/. Voz (Swift). Install and API: https://desertant.com/docs/voz/. Uhm (Swift). Install and API: https://desertant.com/docs/uhm/. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
A Shortcut that cleans up any audio file's sound.
Build an App Intent for Apple Shortcuts that runs Desert Ant's Clear over an audio file to remove noise and room echo and master it to a chosen loudness, on-device. Build it with the Desert Ant SDK. Clear (Swift, Kotlin, JavaScript / TypeScript). Install and API: https://desertant.com/docs/clear/. Install: SwiftPM desert-ant-core; Maven ai.desertant:clear:3.1.0; npm i @desert-ant-labs/clear @litertjs/core # browser. SDK source: https://github.com/Desert-Ant-Labs/desert-ant-core. Machine-readable catalog of every model and SDK: https://desertant.com/llms.txt.
What the model does
- Trained for a rich, present, close-miked podcast sound: low-mids forward, no thin or distant voice.
- Denoise plus dereverb from a fine-tuned DeepFilterNet 3 model. An untreated bedroom or hotel room comes out closer to a treated studio, with no reverberation added back.
- Sibilance-safe and artifact-free: no harsh peaks on S, T and F, and no pumping or musical noise. Breaths and plosives stay intact.
- Volume presets: Apple Podcasts, Spotify, YouTube, EBU R128 (LUFS / EBU R128 normalization). Output is 48kHz.
- Decodes any audio file AVFoundation can read, and the output extension picks the encoding:
.wavfor 16-bit PCM,.m4a,.mp4, or.aacfor AAC,.cafor.aifffor PCM. Without a filesystem,enhance(bytes:)returns WAV bytes. - Two variants:
clear-studiofor a quiet studio cleanup,clear-naturalto keep room tone. The weights are fetched from the Hub on first use and cached.StrengthandMasteringcontrols on both to adjust to taste.
Getting started
Add speech enhancement to your iOS or macOS, Android or web app in a few lines of code. Clear docs.
// Swift Package Manager
.package(url: "https://github.com/Desert-Ant-Labs/desert-ant-core", from: "3.1.0")
// target dependency
.product(name: "Clear", package: "desert-ant-core")import Clear
let clear = Clear()
let result = try await clear.enhance(path: "in.wav", to: "out.wav")
print(result.realtimeFactor, result.measuredLUFS ?? 0)Add Clear from Desert Ant Labs to this Swift project (iOS, macOS). What it does: On-device Studio Sound for Voice Recordings. SDK: Swift (iOS, macOS) Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme // Swift Package Manager .package(url: "https://github.com/Desert-Ant-Labs/desert-ant-core", from: "3.1.0") // target dependency .product(name: "Clear", package: "desert-ant-core") Reference: - Model page: https://desertant.com/models/clear/ - Full catalog and other models: https://desertant.com/llms.txt Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
// build.gradle.kts (Maven Central)
implementation("ai.desertant:clear:3.1.0")import ai.desertant.clear.Clear
Clear(context).use { clear ->
val result = clear.enhance(samples, 48_000.0) // 48kHz mono out
result.measuredTruePeakDbfs
}Add Clear from Desert Ant Labs to this Kotlin project (Android).
What it does: On-device Studio Sound for Voice Recordings.
SDK:
Kotlin (Android)
Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme
// build.gradle.kts (Maven Central)
implementation("ai.desertant:clear:3.1.0")
Reference:
- Model page: https://desertant.com/models/clear/
- Full catalog and other models: https://desertant.com/llms.txt
Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
npm i @desert-ant-labs/clear @litertjs/core # browser
npm i @desert-ant-labs/clear # Nodeimport { Clear } from "@desert-ant-labs/clear";
const clear = await Clear.load();
const result = await clear.enhance(samples, 48_000); // Float32Array in, 48kHz out
await clear.enhance(samples, 48_000, { targetLUFS: "spotify" });Add Clear from Desert Ant Labs to this JavaScript / TypeScript project (Web, Node.js). What it does: On-device Studio Sound for Voice Recordings. SDK: JavaScript / TypeScript (Web, Node.js) Repo: https://github.com/Desert-Ant-Labs/desert-ant-core#readme npm i @desert-ant-labs/clear @litertjs/core # browser npm i @desert-ant-labs/clear # Node Reference: - Model page: https://desertant.com/models/clear/ - Full catalog and other models: https://desertant.com/llms.txt Add the SDK, then follow its README for the exact API and current version. Do not invent API names or method signatures; confirm them against the README.
Specs
- Speed
- 302x realtime on an iPhone 16 Pro
- Model
- Fine-tuned DeepFilterNet 3
- On-device size
- 9.0MB Core ML, 24MB ONNX, per variant
- Platforms
- iOS 18+, macOS 15+, tvOS 18+, visionOS 2+ (Core ML); Android 7+ (LiteRT); the browser (WebAssembly and LiteRT.js); Node
Clear is built for speech. Music, effects, and other non-vocal sound get pulled down as noise, so run Clear on a voice track, not a finished mix.
Clear is not a source separator either: two people talking over each other stay overlapped. clear-studio cleans hard enough to strip breath and room tone, so reach for clear-natural in a treated room.
FAQ
What is Clear?
On-device speech enhancement that gives your recording the warm, close-miked sound of a podcast studio, processed 100% on-device.
Does Clear run on device?
Yes. Clear runs on the device, with no server call, so the data stays with the user.
Which platforms does Clear support?
Clear ships as a native on-device SDK for Swift, Kotlin, JavaScript / TypeScript.
How much does Clear cost?
Every model is free up to 100k monthly active devices per SDK. Unlimited inference per user. Contact us for custom licenses.
How accurate or fast is Clear?
302x realtime on an iPhone 16 Pro and 345x on a MacBook Pro M5: enhance, master, and re-encode a 60-second clip, best of three, on the device.