Promo videos
with a voice-over,
from one sentence.
MaestroCut writes a short spoken line for every scene, records it in a natural neural voice and fits the scenes to the speech. Captions follow the voice word by word, and the music steps back while it talks.
- film styles
- 11
- film styles
- natural voice-over
- TR · EN
- natural voice-over
- every platform size
- 9:16 → 16:9
- every platform size
Films made with it
Swipe
A voice-over promo video says the offer out loud while the screen shows it, and its captions keep it clear with the sound off. MaestroCut writes one short spoken line per scene from your brief, records it in a natural Turkish or English neural voice at 0.8–1.25× speed, lengthens each scene to fit its line in whole bars of the music, dips the music under the speech and shows captions that follow the voice word by word.
How it works
- 01
Describe it
One or two sentences about what you promote. The director writes the script and plans the scenes first.
- 02
Add the voice
One click writes a spoken line for each scene and records it: Turkish or English, a female or male voice, at 0.8–1.25× speed.
- 03
Edit and export
Change any line and record it again, pick a caption style, then export a 1080p MP4 with the voice and music mixed.
Voice-over and captions at a glance
What the studio offers today.
| Languages | Turkish and English |
|---|---|
| Voices | Natural neural voices: Turkish female or male, American English female or male, British English female |
| Speed | 0.8× to 1.25× |
| Caption styles | Pop, karaoke, clean, or off |
| Caption position | Bottom or middle, inside the platform's safe zone; at most two lines at a time |
| Scene timing | Each scene grows to fit its spoken line, rounded up to whole bars, so cuts stay on the beat |
| Music | Dips under the voice while it speaks; the voice is leveled to a steady loudness |
| Editing | Every line is editable and can be re-voiced; removing the voice-over restores the original scene lengths |
Source: MaestroCut studio (2026-10)
Captions in three styles, or none
Captions come from your script, so every word is spelled the way you wrote it.
Pop
Heavy display type with an outline; each spoken word springs up in your accent color.
Karaoke
The whole line stays on screen and fills with the accent color word by word, in time with the voice.
Clean
Plain lines on a small rounded plate that fade in and out: calm and easy to read.
Off
No captions: the voice and the on-screen copy carry the message.
Frequently asked questions
Which languages and voices are available?
+
Turkish, with a female or a male voice, and English, with American female and male voices and a British female voice. All are natural neural voices.
Can I change what the voice says?
+
Yes. Every spoken line is editable: change the words, the voice or the speed and record it again. Removing the voice-over brings back the original scene lengths.
Do the captions work with the sound off?
+
Yes. Every spoken word appears on screen as it is said, in pop, karaoke or clean style. Captions are taken from your script, not transcribed, so there are no misheard words.
Does the voice-over change the length of the video?
+
It can: a scene grows when its line needs more time, rounded up to whole bars of the music, so every cut still lands on the beat.
Will the music drown out the voice?
+
No. The music dips while the voice speaks and comes back between lines, and the voice is leveled to a steady loudness.
What does it cost?
+
Previews and edits are free; credits are spent when you export, per second of video. A 30-second HD export costs 30 credits, and you get 60 free credits on sign-up.
Keep exploring
Industry playbooks
Guides
Free tools
Make a promo video that speaks
Describe it in a sentence; the script, voice, captions and music are ready to edit.