0:57
Whitespace Launch
Whitespace · B2B · Jul 2026
Explore
AI at Meta - 🔉 Introducing SAM Audio, the first unified model that isolates any so
Meta · Dec 2025 · 1:09 · AI-annotated
- Length
- 1:09
- Scenes
- 25 · 2.8 s avg
- Product on screen
- 0:00
- Features shown
- 4
- Call to action
- 0:59 · 86%
- Voiceover
- Yes
00:00:00 / 01:09:01
Meta’s 1:09 launch film runs 25 scenes, about 2.8 s each. The product is on screen from the first frame and 4 features are revealed. The call to action lands at 0:59 (86% in), over a voiceover. A black-field launch film built as a title-card index: an intro card, then four feature chapters, each opened by an oversized white headline that scales past the frame edges and closed by a short live-action demo where a neon outline snaps around the subject and a pill-shaped waveform bar isolates its sound. Pacing is brisk at roughly 13 cuts per minute with locked-off title frames for contrast, and the video resolves on a URL card followed by the Meta logo.
Footage neededEstimated needs: 3 capture groups — your screens or recordings · 1 official logo — reused across the film · 13 filmed passages — shoot, supply or replace
Is this your launch? to your site or press kit.
More like this
1:03
Superhuman - Introducing our new enterprise AI features! With Grammarly Business,
Superhuman · Productivity · Jun 2023
1:46
AI at Meta - 🔉 Introducing SAM Audio, the first unified model that isolates any so, scene by scene
· 25 scenes as text
01 · Product intro · 0:00–0:03
On a black field, a small 'Introducing' scales in above the large white title 'SAM Audio', which reveals left to right as thin light trails swirl around it. A caption line then appears at the bottom of the frame.
On-screen text: “Introducing”, “SAM Audio”, “Introducing SAM Audio”, “A state-of-the-art model”
Techniques: Kinetic type
Camera: Push in
02 · Product intro · 0:03–0:03
On a black background, a white title card reads Introducing SAM Audio with a small tagline below; Introducing scales while the title holds. The title then clears and four rounded video clips of people in everyday settings fade into a staggered grid, the tagline staying put.
On-screen text: “Introducing”, “SAM Audio”, “A state-of-the-art model”
Techniques: Kinetic type
Camera: Push in
03 · Product intro · 0:03–0:05
Four video clips form a collage on black: violin hands, a woman on a call, two street performers, a man with a mic. Green and blue outlines trace the woman and singer, each with a waveform and round control. White captions build at the bottom.
On-screen text: “A state-of-the-art model”, “for isolating sounds in music, speech and general sounds.”
Techniques: Split screen
Camera: Push in
04 · Product intro · 0:05–0:05
Four video tiles on black show a violinist, a woman on the phone, a gesturing woman, and a man singing. Green and blue outlines track the speakers, each with a waveform bar labeled 'Singer'. A bottom caption reads 'for isolating sounds in music, speech and general sounds.' Tiles zoom slowly.
On-screen text: “for isolating sounds in music,”, “speech and general sounds.”
Techniques: Split screen
Camera: Push in
05 · Product intro · 0:05–0:06
Four rounded video clips fade in and scale up on black: a man in a maroon jacket, a DJ in green light, a plane in blue sky, and a corgi. A circular play button appears at left while a white caption sits at the bottom.
On-screen text: “for isolating sounds in music,”, “speech and general sounds.”
Techniques: Split screen
Camera: Push in
06 · Product intro · 0:06–0:08
Four rounded video tiles fill a black field: a man with an orange outline, a DJ under green light, a plane, and a barking corgi. The tiles spread and scale up as a pink outline traces the DJ and a 'Music' chip pops in. A caption anchors the bottom.
On-screen text: “for isolating sounds in music, speech and general sounds.”
Techniques: Split screen
Camera: Push in
07 · Feature reveal · 0:08–0:09
A bald man in a maroon jacket, rimmed by a glowing orange outline, holds on the left in a dark room. The frame then cuts to black and the words Text Prompt scale up in the center.
On-screen text: “Text Prompt”
Techniques: Kinetic type
Camera: Static
08 · Feature reveal · 0:09–0:11
On a black field, the white headline “Text Prompt” scales up from the center until it overflows both edges, while the smaller caption “Separate audio with text prompts.” holds still at the bottom.
On-screen text: “Text Prompt”, “Separate audio with text prompts.”
Techniques: Kinetic type
Camera: Static
09 · Feature reveal · 0:11–0:14
A band plays rock music in a workshop, a guitarist on the left and a drummer on the right. A dark search bar fades in at the center as the word guitar is typed into it, and a caption at the bottom reads [Band playing rock music].
On-screen text: “[Band playing rock music]”
Camera: Pull out
10 · Feature reveal · 0:14–0:18
A band plays in a workshop as a search pill reading “guitar” morphs into a “Guitar 1” bar with an animated waveform; a yellow outline traces the white guitar. Captions switch from [Band playing rock music] to [Isolated guitar], then bottom text appears.
On-screen text: “guitar”, “[Band playing rock music]”, “Guitar 1”, “[Isolated guitar]”, “or extract a sound using visual prompts.”
Techniques: Morph
Camera: Pull out
11 · Feature reveal · 0:18–0:20
On a black field, the white word “Visual” grows into “Visual Prompt” and keeps scaling until it overflows the frame, while a small caption sits still at the bottom.
On-screen text: “Visual Prompt”, “or extract a sound using visual prompts.”
Techniques: Kinetic type
Camera: Static
12 · Feature reveal · 0:20–0:29
A woman on a phone in front of a blurred red coaster. A green sketch outline traces the passing train and a cursor points to it; a blue outline then traces the woman as a labeled waveform bar appears. Subtitles run along the bottom.
On-screen text: “Hey! Hang on. Can you hear me?”, “It's super loud.”, “[Train sound]”, “You know what, actually, it's better.”, “You will not believe the day that I've had.”
Techniques: Cursor demo
Camera: Push in
13 · Feature reveal · 0:29–0:32
On a black field, the white headline 'Span Prompt' scales up from the center until it overflows the frame edges. A smaller two-line white caption, 'Use a span prompt to get even more precision,' appears below. The frame stays locked off.
On-screen text: “Span Prompt”, “Use a span prompt”, “to get even more precision.”
Techniques: Kinetic type
Camera: Static
14 · Feature reveal · 0:32–0:38
A full-frame shot of a seagull in dry grass under a dark blurred background, with a dark audio-waveform bar across the top. A white cursor clicks the waveform, blue bars light up, and a blue selection outline snaps around the seagull as the bottom caption shortens.
On-screen text: “[seagull cawing and ocean waves]”, “[seagull cawing]”
Techniques: Cursor demo
Camera: Static
15 · Feature reveal · 0:38–0:40
A white headline “Multi Prompt” sits centered on a black field and scales up continuously until it overflows the frame. Below it, a two-line caption fades in from gray to white and holds still.
On-screen text: “Multi Prompt”, “or combine multiple prompts”, “to dial in your workflow.”
Techniques: Kinetic type
Camera: Static
16 · Feature reveal · 0:40–0:49
Two people talk at a cafe table as a search bar overlay types 'speech', then Speaker 1 and 2 transcript bars with waveforms appear while orange and blue outlines track each person and cursors point to them. Subtitles run along the bottom.
On-screen text: “or combine multiple prompts to dial in your workflow.”, “I just have to double check to make sure that it wasn't canceled...”, “because you know that uh, instructor is a little flaky.”, “No, check in now otherwise he's going to follow up with you.”
Techniques: Cursor demo
Camera: Static
17 · Demo · 0:49–0:50
A singer performs on a lit concert stage before a crowd. A translucent bar with a blue dot, Mix and a waveform spans the frame, then a second bar with a yellow dot and Guitar slides in above. A dark caption box of white text sits at the bottom.
On-screen text: “SAM Audio is a cutting edge audio model with applications for musicians,”
Camera: Static
18 · Demo · 0:50–0:52
A dimmed concert shot of a singer at a microphone fills the background as five translucent UI rows, Vocals, Guitar, Mix, Drums and Bass, with bouncing waveforms enter one by one over it, while a caption box states the SAM Audio line at the bottom.
On-screen text: “SAM Audio is a cutting edge audio model with applications for musicians,”
Camera: Static
19 · Demo · 0:52–0:53
Five semi-transparent rows labeled Vocals, Guitar, Mix, Drums and Bass, each with a colored dot and a live waveform, sit over a blurred shot of a blonde performer on stage. A dark caption box at the bottom carries the SAM Audio line.
On-screen text: “SAM Audio is a cutting edge audio model with applications for musicians,”
Camera: Static
20 · Demo · 0:53–0:54
Five semi-transparent bars with colored dots and labels for Vocals, Guitar, Mix, Drums, Bass sit over a blurred stage shot of a guitarist, each bar showing an animated white waveform. A dark caption box at the bottom carries the voiceover text.
On-screen text: “SAM Audio is a cutting edge audio model with applications for musicians,”
Camera: Static
21 · Demo · 0:54–0:55
A man in glasses and a mauve cardigan holds a microphone, traced by a glowing pink outline against a blurred street. A waveform bar and a Speech label float at chest height while a dark caption box sits below. He smiles and lifts the mic.
On-screen text: “audio engineers, video creators, and tinkerers of all skill levels.”
Camera: Static
22 · Demo · 0:55–0:57
From behind the audience, a woman in a yellow turtleneck stands at a podium, traced with a pink neon outline, while an asteroid in a circle fills the screen behind. A pill with a pink dot and an animated waveform floats right; a black caption box sits at the bottom.
On-screen text: “audio engineers, video creators, and tinkerers of all skill levels.”
Camera: Static
23 · Demo · 0:57–0:59
Two hosts sit at a table in a purple-lit studio, each traced with a glowing outline, orange and purple. Two translucent waveform bars labeled Speaker 1 and 2 pulse in sync with their voices while a bottom caption swaps from the skill-levels line to a call to action.
On-screen text: “audio engineers, video creators, and tinkerers of all skill levels.”, “Learn more about SAM Audio today.”
Camera: Static
24 · CTA · 0:59–1:04
A black frame holds a centered lockup that fades in: small gray “Learn more at” above a large white “segment-anything.com”. A white caption at the bottom reads “Learn more about SAM Audio today.” and fades out. The lockup then scales up to fill the width.
On-screen text: “Learn more about SAM Audio today.”, “Learn more at”, “segment-anything.com”
Techniques: Kinetic type
Camera: Static
25 · Outro · 1:04–1:09
On a black background, the Meta logo fades in: a blue infinity symbol left of the white Meta wordmark. The mark brightens over the first second, then holds still on a locked-off frame.
Camera: Static