New: Studio Sound v4

Replace the Dolby.io Enhance API.

The Cleanvoice API covers what Enhance did: noise reduction, loudness leveling and speech isolation. You send a file URL and a few boolean flags in one request, then poll for the result. The Python and JavaScript SDKs do the polling for you.

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.

Read the docs
Veed
bHuman
Altered
Thames College
Teleprompter
Natural Reader
Veed
bHuman
Altered
Thames College
Teleprompter
Natural Reader

What happened to Dolby.io

Dolby.io, the Enhance product page (dolby.io/products/enhance) and the Media API docs all return a 301 redirect to optiview.dolby.com. Dolby OptiView sells live-sports streaming, ad insertion, a video player (formerly THEOplayer) and sports analytics, and neither its product list nor its docs mention Enhance or the Media APIs. The Enhance endpoint still responds and asks for credentials. We could not find a published end date or a migration guide from Dolby.

Each Enhance feature and its Cleanvoice flag

Every flag is a boolean in the config object, so most of the migration is deciding which ones to turn on.

Every option in the docs →
Noise reduction
remove_noiseSet remove_noise to true to strip background noise. For the full cleanup in one pass, studio_sound handles noise as well.
Loudness leveling
normalizeDolby's loudness leveling maps to normalize. Turn it on next to any other flag in the same request.
Speech isolation
studio_soundDialog isolation maps to studio_sound, which runs Studio Sound v4, our speech enhancement model. It fixes reverb and background noise, muffled or thin voices, distortion and old recordings in one pass.
Content-type presets
studio_soundEnhance asked you to pick a preset such as podcast, meeting or interview. Studio Sound v4 is one model, so there is no preset parameter to set.
Workflow and storage
input.filesDolby read the file from its own storage or from a URL to your cloud storage. Cleanvoice takes a public or signed URL in input.files, so your files can stay in your bucket.

Swap the Enhance call for one request.

studio_sound covers noise, leveling and speech isolation in one pass; normalize evens out the loudness. Add any editing flag next to them.

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

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

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.

Questions about moving off Dolby.io

Still have a question?

Send it over and a real person will answer.

support@cleanvoice.ai
Ask Now

When we checked in October 2026, the Enhance endpoint still responded and asked for credentials. Dolby no longer markets or documents it: dolby.io and the Media API docs redirect to optiview.dolby.com, and the OptiView product list does not mention Enhance. We could not find a published end date or a migration guide.

Use remove_noise for noise reduction and normalize for loudness leveling. For speech isolation, or for the whole cleanup in one pass, set studio_sound. The same request can also cut filler words, long silences, mouth sounds, breaths and stutters, and return a transcript and a summary.

No. Cleanvoice reads each file from a URL, so a signed URL to your existing bucket works. Processed files are kept for 7 days and then deleted, and audio is never used to train models. The service is EU-hosted, GDPR compliant and ISO 27001 certified.

Cleanvoice has no equivalent for either, so if your product depends on them you will need another provider for that part. For speech cleanup, the API accepts .mp3, .wav, .m4a, .flac, .mp4, .mov and .mkv directly, and a video comes back as video.

By the length of the audio, rounded up to the minute. You can pay as you go or subscribe, there are no seats, and failed jobs are not charged. Startups can request up to 200 hours of free API credit from the API Keys page in the app.

Sign up to get free credits, create a key, and send one of the files you used to test Dolby through /v2/edits with studio_sound on. A 2 to 3 minute clip comes back in about 30 seconds; an hour of audio takes 5 to 10 minutes.

Get your API key.

Sign up, copy your key and send your first file.

Get your API keyBook a call