Audio separation for media and broadcast

Isolate voice from any broadcast or video

Isolate voice from any video or audio. Get a clean dialogue stem, with the music and effects (M&E) on a stem of their own.

CH 01 Interview
Original mix
Channel
Voice
0 dB
Street
0 dB

  • Batch

    Video and audio files, in Studio or by API

  • Live

    Live broadcasts in real time. Enterprise, on request

Trusted with live broadcasts

Ligue 1
FanCode
Australian Open
NASCAR
MLS
YES
Ligue 1
FanCode
Australian Open
NASCAR
MLS
YES
Ligue 1
FanCode
Australian Open
NASCAR
MLS
YES
Ligue 1
FanCode
Australian Open
NASCAR
MLS
YES

CAMB.AI runs live multilingual broadcasts for Major League Soccer and the Australian Open. See our media work

Two stems

More than a voice isolator

Most voice isolators keep the voice and throw the rest away.

CAMB.AI gives you both: a clean dialogue stem and an M&E stem with the music, effects and ambience. Use the dialogue for subtitles and transcripts, and the M&E for dubbing.

Live · Enterprise

Isolate voice from a live broadcast

Separate voice and background in real time on live broadcasts, events and streams. We set it up with your team, on your own feed.

  • Voice and background as two live streams
  • Any language, several speakers at once
  • Straight into CAMB.AI live translation and dubbing
Newsroom feedMove the level to bring the studio back0:00
Voice
Studio

Side by side

Cleaner than AudioShake and ElevenLabs on all 8 measures

CAMB.AI

Tap a stem to hear it

Less noise between words

 vs AudioShake

 vs ElevenLabs

Benchmark

A voice isolator you can measure

On the same seven real-world clips, including a live newsroom, archival TV and an outdoor interview, CAMB.AI beat both ElevenLabs Voice Isolator and AudioShake on every measure.

The cleanest voice of the four

2.8× AudioShake and 1.7× ElevenLabs on how cleanly the voice is pulled from the mix.

SI-SDR, estimated by SQUIM: how much of the separated voice is the voice and not what was around it.

CAMB.AI2.84 dB
AudioShake1.01 dB
ElevenLabs1.64 dB
LALAL.AI2.81 dB

CAMB.AI2.84 dB
LALAL.AI2.81 dB
ElevenLabs1.64 dB
AudioShake1.01 dB

The cleanest voice of the four

2.8× AudioShake and 1.7× ElevenLabs on how cleanly the voice is pulled from the mix.

SI-SDR, estimated by SQUIM: how much of the separated voice is the voice and not what was around it.

CAMB.AI0.376%
AudioShake0.437%
ElevenLabs0.447%
LALAL.AI0.529%

The least voice left behind

14% less than AudioShake, 16% less than ElevenLabs, 29% less than LALAL.AI: a background stem you can really reuse.

Average probability that speech is still heard in the background stem.

CAMB.AI1.895
LALAL.AI1.852
ElevenLabs1.544
AudioShake1.527

The voice that sounds best

24% above AudioShake and 23% above ElevenLabs on how good the separated voice sounds.

PESQ, estimated by SQUIM: perceived speech quality, without a reference recording.

CAMB.AI0.744
LALAL.AI0.740
ElevenLabs0.726
AudioShake0.697

The voice that is easiest to understand

Every word stays clear, ahead of all three.

STOI, estimated by SQUIM: how intelligible the separated speech is.

CAMB.AI0.258
LALAL.AI0.255
ElevenLabs0.229
AudioShake0.209

The most voice in the voice stem

23% above AudioShake and 13% above ElevenLabs.

Average CLAP speech-focus gap: how clearly the foreground stem is about speech.

MeasureCAMB.AIAudioShakeElevenLabsLALAL.AI
Separation quality (SI-SDR)2.84 dB1.01 dB1.64 dB2.81 dB
Voice left in the background (Leakage)0.376%0.437%0.447%0.529%
Perceptual quality (PESQ)1.8951.5271.5441.852
Intelligibility (STOI)0.7440.6970.7260.740
Voice kept in the foreground (CLAP gap)0.2580.2090.2290.255
DNSMOS speech quality (SIG)2.6622.3872.5232.684
DNSMOS background quality (BAK)2.8842.3072.5382.973
DNSMOS overall quality (OVRL)2.3031.9232.0942.327

Internal benchmark: CAMB.AI, AudioShake, ElevenLabs and LALAL.AI on the same seven clips from Wikimedia Commons (gaming commentary, a film trailer, live music, an outdoor interview, a live newsroom, archival TV and a red carpet interview), averaged. SQUIM and DNSMOS are reference-free estimates. On the three DNSMOS scores LALAL.AI is slightly ahead; CAMB.AI leads every other measure.

Use cases

Where clean dialogue matters

Dubbing and localization

Dubbing and localization

Replace the voice and keep the original music and sound under it. The M&E stem is ready for every new language.

AI dubbing
Subtitles and transcripts

Subtitles and transcripts

Clean dialogue makes speech easier to transcribe and subtitle.

Subtitles
News and field reports

News and field reports

Rescue interviews recorded on streets, in crowds and in wind.

Post-production

Post-production

Dialogue isolation for edits, re-mixes and promos, without the original session.

Archives

Archives

Bring old programs back with clean dialogue, ready to subtitle, translate or re-edit.

The M&E stem

Need the opposite? Remove voice from video

Keep the M&E stem and drop the voice: music, effects and atmosphere without the dialogue, ready for a new voice-over or a new language.

Dub it into a new language

Live and batch

Isolate voice, live or from files

LiveEnterprise

Separate voice and background in real time on live broadcasts, events and streams. An enterprise feature, set up with your team on request.

Talk to us

Batch

Upload .mp4, .mov, .mp3, .wav, .flac or .aac. Download FLAC, WAV, MP3 or AAC. 22.6 seconds to process a 30-second video.

API

Send whole libraries through the API and get the results in bulk.

POST /apis/audio-separationGET  /apis/audio-separation/{task_id}GET  /apis/audio-separation-result/{run_id}POST /apis/audio-separation-results
See the audio separation API

Built for media companies

CAMB.AI is SOC 2 compliant and doesn't train its models on your audio. Your runs are in your History and you can delete them whenever you want.

More audio separation

Built for

From the newsroom to the archive

Newsrooms

Interviews from streets, crowds and wind, clean enough to air.

Broadcasters

A clean voice for live translation, and the background for every new language.

Post-production

Dialogue isolation for edits, re-mixes and promos.

Localization teams

A clean voice to translate and a background stem to dub over.

Archives

Old programs back with clean dialogue.

How it works

Isolate voice in three steps

01

Upload or connect

A file or a folder. Enterprise teams can also connect a live feed.

02

Separate

CAMB.AI splits the voice from everything else, in any language.

03

Use both stems

Download them, or send the voice straight to subtitles, translation and dubbing.

Pricing

Pick your hours. Both stems in every plan.

Every plan gives you the voice and the background as two stems, in Studio and by API. Try any plan free for 3 days, with 30 minutes of audio.

10 h
Billing

Solo

$40/month

$480 billed yearly

3 hours of audio a month

For creators and hobbyists. Pull the voice out of songs, podcasts and videos in minutes.

Start free trial
  1. Today 30 minutes to try. $0 today.
  2. Day 3 Your plan starts: $480 a year.

Session

Recommended

$130/month

$1,560 billed yearly

10 hours of audio a month

For producers and content creators working every week. Enough for full albums, podcasts and soundtracks.

Start free trial
  1. Today 30 minutes to try. $0 today.
  2. Day 3 Your plan starts: $1,560 a year.

Catalog

$375/month

$4,500 billed yearly

30 hours of audio a month

For professionals and teams at volume. Clean voice and background stems for music, post-production and localization.

Start free trial
  1. Today 30 minutes to try. $0 today.
  2. Day 3 Your plan starts: $4,500 a year.

Enterprise

High volumes, live separation on your own feeds, or separation inside your own workflow.

  • Live separation, in real time
  • Volume pricing
  • SLA and dedicated support
  • Custom delivery and storage

FAQ

Questions about isolating voice

Upload the .mp4 or .mov file in Studio, or send it through the API. Download the dialogue stem and the M&E stem as FLAC, WAV, MP3 or AAC.

A voice isolator separates speech from everything else in a recording. CAMB.AI's AI voice isolator gives you two stems: the dialogue, and the background with music, effects and noise.

Yes. Every run returns both stems, so you can remove the voice from a video as easily as you isolate it.

Yes, as an enterprise feature. Talk to us and we set it up on your own feed: you get the voice and the background as two separate streams in real time.

Yes. All speakers stay together in the dialogue stem.

Separation works on speech in any language.

Noise reduction cleans one track. Audio separation splits the recording into two stems, so you keep the background and can reuse it.

Yes. Create separation tasks, check their status and get the results one by one or in bulk.

Isolate voice from your own footage

  • SOC 2 compliant
  • Your audio isn't used to train our models
  • Batch and live