Write in English.
Speak in your voice.
Record a minute of your voice once — then type English and hear yourself say it, character and all.
Record once
30–60 seconds of your English — accent and all, that is the point. One take, kitchen table is fine.
Type English
Paste your script — up to 2 000 characters a clip. Tune stability and delivery if you want; the defaults are already right.
Publish
Download studio-loudness MP3s that drop straight into your edit. No cleanup pass needed.
Why I built this
I make things in a language 1.3 million people speak. The audience I want lives in English. Subtitles felt like a compromise, and the stock AI voices sounded like nobody — least of all me. dub44 is the tool I wanted to exist: my voice, fluent English, five minutes from signup to a clip I'd actually publish.
Pricing
Generation runs on real GPUs, so the free trial is short but honest: 2 minutes of your cloned voice, 7 days, no card. Upgrade when you've heard it.
Starter
- ✓ 60 min / month
- ✓ 1 voice
- ✓ No watermark
Creator
Popular- ✓ 200 min / month
- ✓ 3 voices
- ✓ No watermark
Pro
- ✓ 600 min / month
- ✓ 10 voices
- ✓ No watermark
Prices exclude VAT where applicable — tax is calculated at checkout.
Questions, answered
Which language should I record in?+
Record in the language you plan to publish in — for most people here, English. The clone copies how you pronounce things, so an English sample is what teaches it your English: your accent, your vowels, your rhythm. Record in Estonian and it still sounds like your voice, but it borrows someone else's pronunciation for the English words.
How much audio do you need?+
30–60 seconds in a quiet room, one take. The model itself only listens to about ten seconds — recording longer just gives us more to choose from, and we pick the liveliest stretch automatically.
Is my voice data safe?+
Your voice is the most personal data there is, and I treat it that way: stored encrypted in the EU (Frankfurt), never shared, never used to train models, deleted for real when you delete your account.
Can I clone someone else's voice?+
Only with their explicit permission — you confirm that every time you create a voice. Every generated file carries an inaudible provenance watermark.
What does the trial include?+
2 minutes of generated audio over 7 days, one voice, no credit card. Trial clips carry a short audible tag; paid plans have none.
Can I use the audio commercially?+
Yes — on paid plans everything you generate with your own voice is yours to publish, monetized videos included.