# Clean song maker: make a clean version of a song

Censor explicit lyrics while drums, bass, and synths keep playing underneath.

Powered by [Bleep censor](https://audo.ai/bleep-censor.md) — vocal separation so the beat plays on under every muted word.

## How it works

1. Drop your explicit song (WAV, MP3, M4A, AAC, or a music video) up to 10 GB.
2. Keep Keep the beat on, pick Mute for a vocal drop or Bleep for a tone, and add custom slang under Also censor (up to 200 entries).
3. Check starred lyrics across repeated choruses — untick false hits via Censor only these when signed in — and download your clean track.

## Where DJs, coaches, and creators censor songs

Create smooth radio vocal drops without punching awkward silent holes through 808s, hi-hats, or guitar chords.

### Weddings, proms & DJs: Radio edit maker for school dances, receptions, and live sets

Album cuts, underground remixes, and SoundCloud edits often have no official clean release. Keep the beat isolates the vocal stem before muting swear words, so kick drums and basslines ride uninterrupted across the dancefloor.

### Spin, HIIT & dance studios: Censor song playlists for fitness classes and youth warmups

Switch Swear words from Strong to Strong and mild for all-ages gyms, cheer routines, and stadium PA warmups so mild words like damn and hell drop out alongside heavy profanity without altering track BPM.

### Slang & repeated hooks: Catch regional slang, ad-libs, and chorus variations

Add up to 200 artist-specific slang words, drug references, or prefix wildcards under Also censor (plus safe homophones under Leave in), then scan the starred lyric breakdown to confirm every hook pass.

### Music videos & Reels: Clean performance videos or pull full instrumentals

Upload an MP4 or MOV music video to clean explicit vocals while copying 1080p or 4K picture bit-for-bit — or strip singing from start to finish in [Vocal remover](https://audo.ai/vocal-remover.md) and [Karaoke maker](https://audo.ai/karaoke-maker.md).

## How vocal separation keeps the beat intact under muted lyrics

Powered by Audo and its [Bleep censor](https://audo.ai/bleep-censor.md) engine, this clean song maker turns explicit songs across MP3, WAV, M4A, FLAC, AAC, OGG, Opus, AIFF, and music videos up to 10 GB into radio edits — where the first minute is free per track, 3 times a day, with no sign-up and Keep the beat included.

Muting a mastered stereo song on a timeline silences snares, bass, and synths alongside the singer. With Keep the beat on by default, Audo splits singing vocals from the instrumental first, places quiet-valley edges (10 ms windows at 5 ms steps) with 8 ms fades around each explicit lyric on the vocal stem alone, and mixes the untouched instrumental back underneath so track length and DJ beatgrids stay locked.

Built-in Strong and Strong and mild lists cover 7 languages (English, Spanish, French, German, Portuguese, Italian, and Dutch), while custom words and wildcards work in 60 languages. Because fast rap, pitch effects, or layered vocals can hide words from transcription, check the starred lyric list after running, refine hits with Censor only these, or extract full instrumentals in [Vocal remover](https://audo.ai/vocal-remover.md) and [Stem splitter](https://audo.ai/stem-splitter.md).

Choosing the right clean-edit settings or music tool on Audo

| Clean-song option | How the edit sounds | Best use |
|---|---|---|
| Keep the beat on + Mute (default) | Clean vocal drop on explicit words while drums, bass, and synths play straight through | Official-style radio edits for DJs, weddings, schools, and fitness classes |
| Keep the beat on + Bleep | Speaker-matched 1 kHz tone (capped at −3 dBFS) on the vocal over continuous music | Comedy tracks, skits, and creator videos where the bleep is part of the joke |
| Swear words: Strong and mild + Also censor | Covers major profanity, mild curses, and up to 200 custom slang or wildcard terms | Youth sports, classrooms, and family venues with strict lyric policies |
| Vocal remover or Karaoke maker | Removes lead singing across the entire song, leaving the instrumental backing | Karaoke nights, freestyle beats, or voiceover background beds |

Tool: Censor audio (`censor_audio`). The same tool's other pages: https://audo.ai/bleep-censor.md, https://audo.ai/audio-redaction.md. Price: 3 credits a minute — $0.03/min ($1.80/hr), or $0.01/min ($0.60/hr) with transcript_file_id, +$0.01/min (+$0.60/hr, $0.03 paid-run min) with pii, +$0.05/min (+$3.00/hr) with keep_background, pay-as-you-go with no monthly subscription — of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@song.mp3 -F sound=mute -F keep_background=true https://audo.ai/api/try/censor-audio -D response.headers -o response.body
```

Read response.headers and response.body before naming media. Handle 202, 200 JSON and errors with the complete response client at https://audo.ai/docs/api?utm_source=markdown&utm_medium=agent#responses.

Free for the first minute of each file, 3 times a day per person, with no key or account. Uploads up to 10 GB, 2 at once from one address. The response is the result itself; a job that runs longer than about 30 seconds returns 202 with a link to check on it. With an API key (`-H "Authorization: Bearer $AUDO_API_KEY"`), omitting free runs the full job with credits if the balance covers it, otherwise the free allowance if quota remains. Set free=true to prohibit spending; for paid runs use free=false with an approved positive max_credits. A free result cut short comes with finishUrl (and the Audo-Finish-Url header when the response is the file itself): give it to the person, who pays there (from $5, no sign-up), and the whole file runs; keep checking the status link, whose finishedBy names the whole-file job and its own status link. Details: https://audo.ai/docs/api.md

## Options

Form fields with the same names as the MCP tool's inputs:

- `profanity`: Which swear words the built-in list censors: strong (strong swear words and slurs), all (also mild ones such as damn, hell, and crap), or none (only words). Lists for en, es, fr, de, pt, it, nl. Default strong.
- `pii`: Personal details (PII) to find automatically in speech: all (names, phone numbers, emails, street addresses, and IDs/numbers), contact (phone, email, address, and IDs/numbers, keeping people's names), or none. Adds 1 credit a minute (at least 3 credits a paid run). Default none.
- `words`: More words or phrases to censor, in any language, up to 200, such as ["acme", "john smith"]. Matched as whole words, ignoring case and punctuation; end one with * to match every word that starts with it, such as "frick*".
- `allow`: Words the built-in list would censor that should stay, such as ["hell", "bloody"]. Default: none.
- `sound`: What a censored word sounds like: bleep (a 1 kHz tone at the voice's own level) or mute (silence). Default bleep.
- `keep_background`: true separates the voice first, so music and sound effects keep playing under each censored word and only the voice is bleeped or muted. Adds 5 credits a minute. Default false: everything is bleeped or muted for the word.
- `dry_run`: true lists the words it would censor, with their IDs and times, and makes no file. Default false.
- `censor_ids`: Censors only these, by ID from a dry run with the same transcript, such as ["w12", "w48"]. Needs transcript_file_id. Default: everything found.
- `language`: The spoken language, as a code such as en or es. It picks the swear word list: en, es, fr, de, pt, it, nl. Default: detected.
- `output_format`: The result's format: same (as the input; a video stays a video), wav, mp3, m4a, or flac. Default same.

## Languages

Transcription recognizes 60 languages, so automatic AI PII detection (`pii: "all"` or `"contact"`) and custom words and phrases in `words` (plus `allow` lists and pre-starred transcript words) work in all 60 languages. Built-in swear-word and slur lists (`profanity: "strong"` or `"all"`) cover 7 languages: `en` English, `es` Spanish, `fr` French, `de` German, `pt` Portuguese, `it` Italian, and `nl` Dutch.

## From an assistant (MCP)

Add https://audo.ai/mcp and sign in (setup for each assistant: https://audo.ai/setup.md). The tool is `censor_audio`:

> Bleeps or mutes swear words, slurs, spoken personal details (PII), and words or phrases you list, in place: length, timing, and a video's picture stay. pii "all" or "contact" automatically detects spoken personal names, phone numbers, emails, street addresses, and IDs/numbers ("contact" keeps names). Profanity lists for en, es, fr, de, pt, it, nl; your words work in any language. Edges go in the quiet, so no syllable slips through. keep_background keeps music and effects playing under each word. dry_run lists matches with IDs. Not for cutting words out (cut_audio). It costs 3 credits a minute, or 1 with transcript_file_id, plus 1 a minute with pii (at least 3 credits a paid run) and 5 with keep_background, charged only if the job succeeds. Returns the file, each word's times, and a transcript marking them, or job_id for get_job.

Example: "Use Audo to make a clean version of song.mp3, muting swear words and keeping the beat."

## Questions

**Is there a free clean song maker online with Keep the beat included?** Yes, Audo cleans the first minute of each song for free, 3 times a day, with no sign-up and Keep the beat included. Full-length songs cost $0.03 a minute ($1.80 an hour) plus $0.05 a minute ($3.00 an hour) with Keep the beat, and re-editing lyric selections from the saved transcript with Censor only these costs $0.01 a minute ($0.60 an hour) (plus $0.05 a minute ($3.00 an hour) when Keep the beat is on), paid once from $5 with no subscription — [see pricing](https://audo.ai/pricing.md).

**How do I censor song lyrics without making the music drop out?** Leave Keep the beat switched on in Audo above. Instead of muting the combined stereo mix, Audo splits the vocal from drums, bass, and synths first, mutes or bleeps each explicit word on the vocal stem with 8 ms fades and quiet-valley edges, and blends the untouched instrumental underneath.

**What if fast rap verses, slang, or repeated choruses get missed?** Sung melodies and regional slang are harder to transcribe than speech, so Audo shows every flagged word starred in its lyric line. Add missed slang or prefix wildcards (up to 200) under Also censor, list safe words under Leave in, or untick false hits when signed in and press Censor only these to re-render from the saved transcript for $0.01 a minute ($0.60 an hour) (plus $0.05 a minute ($3.00 an hour) when Keep the beat is on).

**Should I choose Mute or Bleep, and will my song's BPM or beatgrid change?** Choose Mute on Audo for a clean radio-edit vocal drop, or Bleep for a speaker-matched 1 kHz tone. Both replace vocal samples in place without adding or removing samples, so song length, tempo, and DJ beatgrids stay locked — check tempo anytime in [Key & BPM finder](https://audo.ai/key-bpm-finder.md).

**Which languages and audio or video formats work?** Audo's Strong and Strong and mild profanity lists cover 7 languages (English, Spanish, French, German, Portuguese, Italian, and Dutch), while custom words work across 60 languages on WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF songs and MP4, MOV, MKV, WebM, AVI music videos up to 10 GB.

**Can I strip all vocals to make an instrumental backing track instead?** Yes, open Audo's [Vocal remover](https://audo.ai/vocal-remover.md) or [Karaoke maker](https://audo.ai/karaoke-maker.md) to pull singing out of the entire song, or use [Stem splitter](https://audo.ai/stem-splitter.md) to separate vocals, drums, bass, and other instruments into four individual stems.

**Can ChatGPT, Claude, or a DJ prep script clean songs automatically with Audo?** Yes, connect Audo via [Add Audo to your assistant](https://audo.ai/setup.md) over MCP so ChatGPT, Claude, Claude Code, or Cursor can run censor_audio with keep_background=true, or automate batch radio edits through the [REST API](https://audo.ai/docs/api.md).

**What happens to my uploaded song files?** Your tracks stay private on Audo: uploaded files are deleted automatically after 24 hours, and signed-out free results expire after 1 hour.

## More

- Other cuts: [Remove filler words](https://audo.ai/remove-filler-words.md), [Bleep censor](https://audo.ai/bleep-censor.md), [AI clip finder](https://audo.ai/ai-clip-finder.md), [Cut audio](https://audo.ai/audio-cutter.md), [Remove silence](https://audo.ai/silence-remover.md), [Trim video](https://audo.ai/trim-video.md), [Audio redaction](https://audo.ai/audio-redaction.md)
- Related guides: [Audio and video tools for AI agents](https://audo.ai/guides/audio-and-video-tools-for-ai-agents.md)
- [All tools](https://audo.ai/all-tools.md)
- [Prices and free limits](https://audo.ai/pricing.md)
- [Set up your assistant](https://audo.ai/setup.md)
- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/clean-song-maker?utm_source=markdown&utm_medium=agent
