Your voice, without the room it was recorded in.
Upscale splits the audio in your video into three layers — the speech, the steady background, and the narrow tones that sit on top — then lets you rebalance them by ear until the voice is the thing people hear.
Then finish the clip. Put a marker on something and it follows. Push the camera in on the line that matters. Save it to Photos, ready to post. The last touches, without opening a full editor.
WHAT IT CLEANS UP
• Fans, air conditioning, hum, traffic and other steady room noise
• Beeps, alarms, birdsong and phone notifications
• Speech that sits too low, too dull, or too uneven
HOW YOU MIX IT
• Voice, Background and Tones each get their own fader — turn the room down, bring the voice up
• Tone runs warm to bright; Loudness lifts the level without crushing it
• Hold Compare at any moment to hear the original against your edit
• Solo any layer to hear exactly what landed in it
The split runs when you ask for it, not on import. Bring in a clip, mark it up and export, and the audio is passed through exactly as recorded.
FOLLOW SOMETHING
Point at a subject and it stays pointed at it, frame by frame, for as long as you asked. A dot on your fingers, a ball, a face, a product in your hand.
• Tap the thing, pinch the ring to fit it, and pick 2, 5, 10 seconds or the rest of the clip
• Give it a name and a line runs out to a label — it unfurls when the marker arrives and packs away when it leaves
• Drag anywhere on the clip to place the label; it stays inside the frame on its own
• Eight colours, on a plate or as bare text over the footage
• As many markers as you like, each with its own colour, name and stretch of the clip
PUSH THE CAMERA IN
Two camera moves, no keyframes to place. A push eases in on the moment that matters and settles back out. A whip snaps in and straight back, throwing the frame up, down, left or right.
• Scrub to the spot, tap one, drag on the clip to aim it, pinch to set how close
• A whoosh that sweeps with the move, a low impact on the landing, or a quiet tick — generated to the exact length of each move, so nothing sits a beat late
EVERYTHING HAPPENS ON YOUR PHONE
No account, no sign-up, no upload. Your video never leaves the device, the app works in airplane mode, and nothing about you is collected.
FREE AND PRO
Every feature is unlocked from the first launch — the split, the faders, tracking, labels, the camera moves, Compare — and every clip gets the full two minutes whether you pay or not. Nothing is held back and nothing is watermarked.
Free includes three exports. After that, Upscale Pro is a one-time purchase, never a subscription:
• Unlimited exports
• Export the isolated voice, background and tone layers as separate audio files
Buy it once and it stays yours, on every device signed in to your Apple Account.
WHEN YOU'RE DONE
Everything you changed is written back into the video and saved to your photo library, ready to post.
GOOD TO KNOW
The audio work is classic signal processing, not AI source separation. It handles fans, hum and room tone well — it can't isolate music or pull apart two people talking at once.
Tracking follows one thing at a time and holds through a hand passing in front of it. Two identical objects crossing — two fingers of the same hand, say — can still confuse it.
Privacy Policy: https://www.velto.at/en/upscalevoice/support
Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/
Show more
