Baby
Clear gain- Overall
- 2.10 → 3.27
- Background
- 2.26 → 4.04
- Naturalness
- 3.37 → 4.70
EraseNoise is a background noise remover that lowers a baby crying or babbling behind the voice in an audio or video file. In our real sample, naturalness went from 3.37 to 4.70 out of 5. Play it below, then preview 30 seconds of your own recording free.
Last updated
Play the baby recording and switch between the original and the cleaned take while the crying is loudest. Then upload your own file and pick a sentence the baby talked over.
In the baby recording, overall quality went from 2.10 to 3.27, background from 2.26 to 4.04, and naturalness from 3.37 to 4.70. A barking dog, the other common sound at home, is next to it. Scores are DNSMOS and NISQA predictions on a 1–5 scale for real crying-baby and related home recordings from the Microsoft DNS Challenge test set, processed with no hand edits.
A baby is a voice too, but not speech. It drops best when the speaker is closer to the mic than the baby.
Crying through a door during a call or an episode. The speaker is closer than the baby, which is the easiest case.
Hear the recordingSofter than the crying we tested and often in the pauses. Expect it to drop at least as well, and check the preview.
A baby right at the mic is as loud as the voice. The cleanup helps, but check the preview closely.
A toddler saying words is speech, and the model keeps speech. Expect some of it to stay.
A cry rises and falls over many seconds, so cutting it out cuts the speaker too.
You do not find and trim every cry. Upload the recording once.
In our sample naturalness rose from 3.37 to 4.70, so the speaker did not come out processed.
Nothing is cut, so the recording keeps its length and a video stays in sync.
Listen to the sentences the baby talked over.
A scream on a word can leave that word rough. Re-record that line if it matters.
If a child spoke real words, some may stay. That is the model keeping speech.
A cry rises and falls over many seconds, which rules out quick cuts.
| Option | Works best when | Falls short when |
|---|---|---|
| EraseNoise | The baby cries behind the speaker for long stretches | The baby is as close to the mic as the speaker |
| Audacity Noise Reduction | Rarely: crying changes pitch and level constantly | The noise is a voice-like cry |
| Cutting in an editor | One short cry falls in a pause | The crying runs under the words |
| Re-recording the line | A podcast line can be read again later | The vows or the toast happened once |
Upload the call, episode, or family video unedited, up to 2 GB.
A work call recorded with the baby awake downloads as WAV.
A family or home video downloads as MP4 with the same picture.
Choose the audio or video file where a baby cries or babbles behind the voice.
Play a sentence the baby cried over, as recorded and cleaned; no account needed.
Process the whole file only if the crying is lower and the speaker sounds like themselves.
A recorded meeting or a client call with crying in the background. Clean the saved file.
The baby woke up halfway through the episode. Clean it instead of starting again.
A baby cried during the vows or a toast on the wedding video. Lower it under the speaker.
Use this page for a baby crying or babbling behind the person talking.
| Job | Use |
|---|---|
| A baby crying or babbling | Use this baby page |
| A dog barking | Remove dog barking from audio |
| Children or adults talking or shouting | Remove yelling noise from audio |
| Laughter in the room | Remove laughing noise from audio |
| A barking dog and other sounds at home, with real audio | Hear all 24 examples |
Recordings of your family stay private: EraseNoise deletes the upload and the cleaned copy 24 hours after upload and never uses them as samples. Save yours that day.
Monthly and yearly prices stay visible together. You pay after the preview sounds right and you keep the full file. Pro includes 20 hours a month, not unlimited cleaning.
Free
Try it on your own recordings
Upload and preview$9.99/month
$9.99/month, or $95.88 per year ($7.99 per month)
For weekly podcasts and video creators
Get StartedBuy minutes once. They do not expire.
1 Hour Pack
$2.99
Pay once, use whenever you need
5 Hour Pack
$9.99
Lower price per minute for bigger projects
| Plan | Price | Includes |
|---|---|---|
| Free | $0 | Free 30-second previews, Unlimited silence removal, Files deleted after 24 hours |
| Pro monthly | $9.99/month | 20 hours of processing per month, Audio and video, Noise and echo removal |
| Pro yearly | $95.88 per year ($7.99 per month) | 20 hours of processing per month, Audio and video, Noise and echo removal |
| 1 Hour Pack | $2.99 | 60 minutes of processing, Audio and video, Minutes never expire |
| 5 Hour Pack | $9.99 | 300 minutes of processing, Audio and video, Minutes never expire |
Upload the recording with the baby in it at the top of the page and compare the free 30-second preview with the original. Download the full file only if the crying is lower and the words are clear.
On a real recording with a baby crying, from the Microsoft DNS Challenge test set, EraseNoise raised DNSMOS overall quality from 2.10 to 3.27 out of 5 and the background score from 2.26 to 4.04. NISQA naturalness went from 3.37 to 4.70, so the speaker sounded more natural once the crying dropped.
Not fully. Words are speech, and the model keeps speech. Crying and babbling drop more than words do.
Yes. Wedding and family videos in MP4, MOV, M4V, or WebM are accepted, and you get back an MP4 with the same footage. Music in the video will be lowered too.
No. EraseNoise works on saved recordings only. On a call in progress, turn on the noise suppression in Zoom, Teams, or Discord, or use Krisp.
Processing time depends on how long the family recording is: as a guide, a 5-minute video takes 10 to 60 seconds. The free 30-second preview of the family recording uses no paid minutes, so you can judge it first.
Up to 2 GB per file. Without an account you can play 3 free 30-second previews in 24 hours, and 20 with one. The full video is billed by the started minute, minimum 1 minute.
Remove noise from audio
Wind, fans, traffic, and hum
Remove noise from video
Clean the soundtrack of MP4, MOV, WebM
Remove echo
A repeat you can count after a word
Remove reverb
Shorten a dense room wash
Audio enhancer
Make speech easier to hear
Remove background music
Lower music under someone talking
Instrumental maker
Take the vocal out of a song
Acapella extractor
Keep only the vocals of a song
Remove vocals from a song
The music stays, the singing goes
Karaoke maker
Turn a song into a backing track
Remove silence
Cut pauses, free and in your browser
Extract audio from video
Save the soundtrack as M4A, MP3, or WAV
Normalize audio
Set loudness to -14 or -16 LUFS, free
Increase video volume
Make a quiet video louder, picture untouched
Remove buzz & hum
Lower electrical hum under a voice
Remove static & hiss
Lower hiss and static under a voice
Remove applause & clapping
Lower claps around a speech
Whether you need to clean a podcast, a meeting, or a video you already shot, these guides show the next step.
Upload one file. Keep the result only if the crying is lower and the voice is unchanged.
Upload your recording