Speech enhancement APIRecord anywhere. Sound like a studio.

Studio Sound v4, our new speech enhancement model, makes any audio or video sound like a studio.

More examples
Tap for sound
Tap for sound
Tap for sound

Or drop a file here, or .

Record up to 15 seconds, or drop audio or video up to 20 MB. Free, no account needed.

Veed
bHuman
Altered
Thames College
Teleprompter
Natural Reader
Veed
bHuman
Altered
Thames College
Teleprompter
Natural Reader

What Studio Sound v4 fixes.

One model fixes all of these in a single pass.

  • Word errors

  • AI voices

  • Call audio

Pricing

From $0.01/ minute of audio

That's $0.60 an hour at enterprise volume, billed monthly or yearly. Self-serve plans from $0.75 an hour, or pay as you go at $1.50.

Compare plans
200 free hours

Startups get up to 200 hours of API credit. Request it from the API Keys page in your dashboard.

Request credits

Raw take in. Studio sound out.

Add studio_sound to the call you already make. Audio or video in, studio sound out.

Every option in the docs →
1from cleanvoice import Cleanvoice
2
3client = Cleanvoice.from_env()
4
5result = client.process(
6    "raw-take.wav",
7    studio_sound=True,
8    normalize=True,
9)
10
11print(result.audio.url)
$ pip install cleanvoice-sdk

Why developers trust us

All your data in your control. Each file processed securely.

  • EU-Hosted

    Servers and GPU located in the EU

  • ISO 27001 & GDPR Compliant

    DPA, SLA and on request even on premise deployment

  • No Training on Your Data.

    We record our own dataset in professional studios.

Speech enhancement for anything with a voice in it

If your users record, upload or generate speech, Studio Sound makes it sound like a studio.

  • Video and podcast platforms

    Give every upload studio sound before it is published, without asking creators to do a thing.

  • Online learning

    Lectures recorded in classrooms and kitchens, sounding like they were made in a booth.

  • Meetings and calls

    Clean up call recordings before they are shared, transcribed or archived.

  • AI voices and text-to-speech

    Fix the artifacts in generated speech, so AI voices sound natural.

  • Dubbing and localisation

    One consistent sound across every language, whatever room each voice was recorded in.

  • Creator and social apps

    Phone recordings that sound like they were made with a real mic.

Questions about Studio Sound

Still have a question?

Send it over and a real person will answer.

support@cleanvoice.ai
Ask Now

An API that takes a recording and returns it with the voice cleaned up: background noise and room echo removed, the tone evened out and the level corrected. With Cleanvoice you send the file URL with studio_sound set to true, and Studio Sound v4 does all of it in one pass.

Noise removal takes the background out. Studio Sound rebuilds the voice itself: loudness normalization, level balancing across speakers, EQ and dereverb, so a laptop recording ends up sounding like it was made in a studio.

Audio and video: .mp3, .wav, .m4a, .flac, .mp4, .mov and .mkv.

Yes, for Python (pip install cleanvoice-sdk) and JavaScript (npm install @cleanvoice/cleanvoice-sdk). Both upload the file, start the job and wait for the result. Any other language can call the REST API with an X-API-Key header.

Studio Sound works on recorded files: you send audio or video and get the enhanced file back in minutes. A real-time SDK for live audio is coming soon. Contact sales if you want early access.

Yes. Next to studio_sound and normalize, the same request can cut filler words, long silences, breaths, stutters and mouth sounds, and return a transcript. One file comes back.

For denoising on your own GPUs, an open model may be enough. Running it yourself means provisioning and scaling GPUs and handling every file format, and denoising covers only part of the job. Studio Sound also takes out reverb, fixes thin and muffled mics and restores old recordings, behind one API call billed per minute of audio.

There is no length limit. For files over 3 GB, write to us and we will set it up with you.

About 5 to 10 minutes for an hour of audio.

By the length of the file, rounded up to the nearest minute, from the same credits as every other Cleanvoice capability. You are not charged if a job fails.

Cleanvoice is EU-hosted and GDPR compliant. Original and processed files are kept for 7 days, then deleted permanently.

Yes. Drop a file in the demo above to hear the first 20 seconds through Studio Sound, no account needed. Startups can also apply for up to 200 hours of free API credit.
30 minutes free

Get your API key.

Sign up, copy your key and send your first file. The first 30 minutes of audio are on us.

Get your API keyBook a call