1:35
Hue (YC F26) Launch Video
Hue · B2B · Oct 2026
Explore
Cartesia - We've raised a $64M Series A led by @kleinerperkins to build the plat
Cartesia · Mar 2025 · 2:55 · AI-annotated
- Length
- 2:55
- Scenes
- 42 · 4.2 s avg
- Product on screen
- 0:00
- Features shown
- 6
- Call to action
- 2:45 · 95%
- Voiceover
- Yes
00:00:00 / 02:55:00
Cartesia’s 2:55 launch film runs 42 scenes, about 4.2 s each. The product is on screen from the first frame and 6 features are revealed. The call to action lands at 2:45 (95% in), over a voiceover. The video alternates between a warm, shallow-depth live-action interview with the CEO and locked-off dark title cards and data graphics, each feature announced by a serif title card and then proven with a chart or a voiced demo. Signature moves are the word-by-word serif type reveals, the sliding panel transitions between data slides, and the stylized characters performing over an animated blue waveform bar.
Footage neededEstimated needs: 1 capture group — your screens or recordings · 1 official logo — reused across the film · 23 filmed passages — shoot, supply or replace · 10 graphic passages — draw or supply · 2 3D passages — build or supply
Is this your launch? to your site or press kit.
More like this
0:58
Alok Bishoyi - Getting your inference right shouldn't be hard. @useRouterPlus (YC
RouterPlus · Oct 2026
0:29
High-Converting Job Search Launch Video | Tsenta
Tsenta · Oct 2026
Cartesia - We've raised a $64M Series A led by @kleinerperkins to build the plat, scene by scene
· 42 scenes as text
01 · Product intro · 0:00–0:02
A man in glasses and a gray cable-knit sweater addresses the camera in a warm cafe interior with pendant lights. A lower-third caption types in at the lower left with his name and title.
On-screen text: “Karan Goel”, “Founder / CEO @ Cartesia”
Techniques: Kinetic type
Camera: Static
02 · Product intro · 0:02–0:11
A man with round glasses and a gray knit sweater speaks to camera in a warm interior, the wooden wall of diamond cutouts blurred behind him. A lower-third caption with his name and title holds at the start, then clears by the middle of the shot.
On-screen text: “Karan Goel”, “Founder / CEO @ Cartesia”
Camera: Static
03 · Problem · 0:11–0:12
A white article card sits centered on dark gray, its image a pixel pattern. It scales up and tilts into 3D as the noise clears into a blue microphone graphic and headline 2025: The Year Voice AI Finds Its Voice; a second card edge enters from the right.
Techniques: 3D mockup
Camera: Pull out
04 · Problem · 0:12–0:14
A dark gray field holds a central white social media card featuring a vintage microphone, surrounded by larger, partially visible article cards. The cluster of cards drifts slowly toward the camera while the background dims, isolating the central element.
On-screen text: “2025: The Year Voice AI Finds Its Voice”, “Why Voice AI Is The New UI?”, “Voice AI to dominate industry in coming years, says SoundHound AI exec”
Techniques: UI zoom, Parallax
Camera: Pull out
05 · Problem · 0:14–0:15
A scattered cluster of voice-AI article cards floats on a dark gray field, drifting and coming into focus. The whole layer then fades out to reveal a bespectacled man in a gray sweater standing in a warm cafe.
Camera: Pull out
06 · Product intro · 0:15–0:16
A man with round glasses and a gray cable-knit sweater speaks directly to camera in a warm kitchen set, gesturing with one hand. The shot holds steady and the image dims toward the end of the clip.
Camera: Push in
07 · Product intro · 0:16–0:19
On a near-black grid background, the line 'Our latest voice foundation model' fades in centered, holds, then fades out as the larger 'Sonic 2.0' fades in at center. Locked-off frame, slow pace.
On-screen text: “Our latest voice foundation model”, “Sonic 2.0”
Techniques: Kinetic type
Camera: Static
08 · Product intro · 0:19–0:20
A near-black background with a faint grid holds the title Sonic 2.0 centered in white serif type. The text settles briefly into a locked position and then holds still for the rest of the clip.
On-screen text: “Sonic 2.0”
Camera: Static
09 · Product intro · 0:20–0:24
A man in round glasses and a gray knit sweater talks to camera in a warm-lit room, a patterned wall blurred behind him. The locked-off medium close-up holds on his face as he speaks, ending on a broad smile. A small lavalier mic sits at his collar.
On-screen text: “Sonic 2.0”
Camera: Static
10 · Feature reveal · 0:24–0:25
A man with round glasses and a mustache smiles in a dim, bokeh-lit room, then the frame cuts to a near-black grid background as the word “Faster,” fades in at center.
On-screen text: “Faster,”
Techniques: Kinetic type
Camera: Static
11 · Feature reveal · 0:25–0:28
A faint grid sits on a near-black field as a centered serif line fades in and sharpens, words resolving left to right into the full claim about the voice model.
On-screen text: “Fastest, most controllable voice model available today”
Techniques: Kinetic type
Camera: Static
12 · Feature reveal · 0:28–0:30
A dark gray data graphic. A black vertical panel slides off the left edge to reveal a pie chart whose slices grow into place, labeled Cartesia 47.7% in blue and ElevenLabs 37.7% in black. A gray circle on the right fills in with a play icon, and a small caption types out along the bottom.
On-screen text: “Win Rate”, “Blinded Human Evals”, “Blinded, head-to-head human prefer”
Techniques: Masking
Camera: Static
13 · Feature reveal · 0:30–0:39
On a dark grid, two pie charts sit side by side under a white serif “Win Rate” title. The right chart scales up from a small white disc into a full pie while its percentages count up, and a monospace caption types out along the bottom.
On-screen text: “Win Rate”, “Blinded Human Evals”, “Blinded, head-to-head human preference evaluations on 100 held out voices.”, “Voice cloning not supported on OpenAI, Azure, Google TTS.”
Techniques: Morph
Camera: Static
14 · Feature reveal · 0:39–0:40
A dark gray data slide titled Win Rate shows two pie charts, Cartesia in blue against ElevenLabs and PlayHT in black. The whole panel slides left as a second Model Latency panel wipes in from the right, its yellow tag and serif title leading the move.
On-screen text: “Win Rate”, “Blinded Human Evals”, “Blinded, head-to-head human preference evaluations on 100 held out voices. Voice cloning not supported on OpenAI, Azure, Google TTS.”, “Blinded Model Latency”, “Model Latency”
Techniques: Masking
Camera: Pan
15 · Feature reveal · 0:40–0:49
A man in a gray sweater talks on the right; a dark panel on the left slides in and builds a latency chart: Sonic 1.0's bar fills to 135 ms, Sonic 2.0 to 90 ms, a blue Sonic 2.0 Turbo bar to 40 ms, numbers counting up.
On-screen text: “Human Evals”, “Model Latency”, “Sonic 1.0”, “135 ms”, “Sonic 2.0”, “90 ms”, “Sonic 2.0 Turbo”, “40 ms”
Techniques: Split screen, Kinetic type
Camera: Pan
16 · Feature reveal · 0:49–0:54
A man in glasses and a gray sweater talks to camera on the right, gesturing. On the left, a static dark bar chart titled Model Latency lists Sonic 1.0 at 135 ms, Sonic 2.0 at 90 ms, and Sonic 2.0 Turbo at 40 ms with a short blue bar.
On-screen text: “Model Latency”, “Sonic 1.0”, “135 ms”, “Sonic 2.0”, “90 ms”, “Sonic 2.0 Turbo”, “40 ms”
Techniques: Split screen
Camera: Static
17 · Feature reveal · 0:54–1:02
A man in round glasses and a gray cable-knit sweater speaks to camera in a medium close-up, gesturing with one hand. The warm background is a blurred wall with a diamond lattice pattern and a small plant at the lower left.
Camera: Static
18 · Feature reveal · 1:02–1:09
On a near-black grid, a horizontal bar chart builds region by region: Asia Pacific, United States, Europe. Each row lists four models; Sonic 2.0 is a short blue bar, OpenAI a long white bar. A serif title and monospace caption type in at the top, then the chart holds.
On-screen text: “P90 Latency (ms)”, “90th percentile latency (including all network and serving latency) from different datacenter locations.”
Camera: Static
19 · Feature reveal · 1:09–1:21
A man in glasses and a gray sweater talks to camera in a warm office with hanging lamps. A black panel slides in from the right, splitting the frame, and a white serif headline sits above four icon labels that type themselves in, one line at a time.
On-screen text: “Spelling is crucial for voice agents”, “names”, “e-mails”, “phone numbers”, “addresses”
Techniques: Masking, Split screen, Kinetic type
Camera: Pan
20 · Feature reveal · 1:21–1:29
On a dark grid background, a pixel-art girl with a headset stands right, above an animated blue waveform, as white serif text types in word by word on the left. The clip ends with a cut to a man in a gray sweater talking in a warm, lamp-lit room.
On-screen text: “Your confirmation number is AT121,”, “and the package will be delivered”, “to 134 Main St.”
Techniques: Kinetic type
Camera: Static
21 · Feature reveal · 1:29–1:33
A man with round glasses and a gray cable-knit sweater addresses the camera in a warm, pendant-lit kitchen, gesturing with his right hand. The shot dims to near black at the end while small white caption lines appear on the left.
On-screen text: “Your confirmation number is AT121,”, “and the package will be delivered”, “to 134 Main St.”
Camera: Static
22 · Feature reveal · 1:33–1:35
A faint grid sits on a near-black field. The blue serif phrase “best in class” glides to the center, then the larger metallic silver serif “Voice cloning” fades in beneath it.
On-screen text: “best in class”, “Voice cloning”
Techniques: Kinetic type
Camera: Static
23 · Feature reveal · 1:35–1:37
A man with dark hair, glasses and a gray sweater speaks in a tight medium close-up against a warm, diamond-patterned wall. The locked-off frame holds on his face as he talks, his head angled slightly off-axis. No camera movement.
On-screen text: “best in class”, “Voice cloning”
Camera: Static
24 · Feature reveal · 1:37–1:38
A man with dark hair, round glasses and a gray cable-knit sweater talks to an off-camera interviewer. The warm brick wall behind him carries a diamond lattice pattern, blurred, with a soft light and plant in the lower left corner.
Camera: Static
25 · Feature reveal · 1:38–1:43
A pixel-art woman stands above a blue audio waveform on a dark grid; she changes to a pixel person with glasses, then to a 3D figure in a red jacket waving, while a white serif sentence builds word by word on the right.
On-screen text: “From just a few seconds of audio, Cartesia can capture even the most nuanced of accents.”
Techniques: Kinetic type
Camera: Static
26 · Feature reveal · 1:43–1:47
A bespectacled man in a gray cable-knit sweater speaks to camera in a warm brick room, gesturing with his hands as caption lines appear. The shot cuts to a black frame holding a small illustrated figure with a microphone above a rounded box containing a blue audio waveform.
On-screen text: “From just a few seconds”, “of audio, Cartesia can”, “capture even the most”, “nuanced of accents.”, “3”
Techniques: Kinetic type
Camera: Static
27 · Feature reveal · 1:47–1:49
A serif caption builds word by word on a dark field beside a painterly figure with a microphone over an animated blue waveform. The scene then cuts to a man in a gray sweater gesturing in a lit office.
On-screen text: “Like a reporter in the middle of a hurricane”
Techniques: Kinetic type
Camera: Static
28 · Feature reveal · 1:49–1:50
A man with glasses and a gray knit sweater faces the camera in a warm office, gesturing with both hands before lowering them. Shallow depth of field blurs the pendant lights and counter behind him.
Camera: Static
29 · Feature reveal · 1:50–1:57
A man in a gray cable-knit sweater and round glasses speaks to camera in a warm room, gesturing with both hands. Behind him, pendant lamps and a kitchen counter sit softly out of focus in a static medium shot.
Camera: Static
30 · Feature reveal · 1:57–1:58
A black title card holds the centered serif title Voice Changer beside a thin line-art magic-wand icon, set over a faint grid. It follows a brief dim shot of a man in a room. The frame stays locked off.
On-screen text: “Voice Changer”
Camera: Static
31 · Feature reveal · 1:58–2:00
A dark title card shows “Voice Changer” beside a wand icon, then “Infill” fades in below with a sparkle icon; the scene cuts to a man in round glasses and a gray sweater speaking against a warm, patterned wall.
On-screen text: “Voice Changer”, “Infill”
Camera: Static
32 · Feature reveal · 2:00–2:04
A man in round glasses and a gray knit sweater talks to camera in a warm-lit room with a diamond-patterned wall; a lavalier mic is clipped to his collar. He raises his hands to gesture mid-sentence.
On-screen text: “Voice Changer”, “Infill”
Camera: Static
33 · Feature reveal · 2:04–2:10
On a black grid, a serif caption types out word by word on the left while a 3D character sits on the right above a waveform bar. The blue throne-bound figure cuts to a hooded figure with a glowing red spine, the caption shifting from white to blue.
On-screen text: “Holy! Ok, I'm alive!”
Techniques: Kinetic type, 3D mockup
Camera: Static
34 · Feature reveal · 2:10–2:15
A man with round glasses and a gray knit sweater talks to camera in a warm, blurred interior, gesturing with his hands. A lavalier mic sits at his collar; diamond-shaped wall panels and a lit plant sit out of focus behind him.
Camera: Static
35 · Feature reveal · 2:15–2:22
A pixel-art man in a tan suit stands left of a near-black frame, an animated blue waveform pulsing in a rounded bar beneath him. A serif sentence types in word by word on the right, the blue underlined name swapping from Catherine to Jennifer to Jonathan.
On-screen text: “Hey Catherine, you should check out Sonic 2.0.”, “Hey Jennifer, you should check out Sonic 2.0.”, “Hey Jonathan, you should check out Sonic 2.0.”
Techniques: Kinetic type
Camera: Static
36 · Other · 2:22–2:26
A man in glasses and a gray cable-knit sweater sits centered in a warm café, speaking to camera. He lifts both hands into a framing gesture mid-sentence. Soft pendant lights and a blurred counter fill the background. White captions appear at the bottom edge.
On-screen text: “Hey Jonathan, you should”, “check out Sonic 2.0.”
Camera: Static
37 · Other · 2:26–2:32
A man with round glasses and a gray cable-knit sweater talks to camera in front of a warm brick wall set with diamond glass blocks. He gestures with one hand while speaking, the background softly blurred by shallow depth of field.
Camera: Static
38 · Other · 2:32–2:37
A man with round glasses and a gray cable-knit sweater sits in a warm, softly lit cafe, speaking directly to the camera. He gestures with both hands as he talks, while pendant lamps and a blurred counter with stools fill the background.
Camera: Static
39 · Feature reveal · 2:37–2:44
On a dark grid background, the serif headline 'Sonic 2.0 runs natively' assembles word by word in the center, blue for 'Sonic 2.0', white for the rest. It then slides up as a blue phone and laptop line icon fade in side by side, labeled 'Phones' and 'Laptops'.
On-screen text: “Sonic 2.0 runs natively”, “Phones”, “Laptops”
Techniques: Kinetic type
Camera: Static
40 · Feature reveal · 2:44–2:45
A man with glasses in a gray sweater stands in a warm kitchen, talking to the camera and gesturing. On-screen text reads “Sonic 2.0 runs natively” as it slides in, with the labels “Phones” and “Laptops” held still.
On-screen text: “Sonic 2.0 runs natively”, “Phones”, “Laptops”
Techniques: Kinetic type
Camera: Static
41 · CTA · 2:45–2:50
A man with round glasses and a gray cable-knit sweater holds a white smartphone in his right hand, raising it as he speaks to camera. He smiles and gestures against a warm tan wall with a diamond lattice of glass blocks. The frame stays locked off on a medium close-up.
On-screen text: “00”
Camera: Static
42 · CTA · 2:50–2:55
A white vertical bar at the center of a dark gray frame breaks apart and reassembles into a pixelated C logo of white squares. The URL sits below it and holds. The frame stays locked off.
On-screen text: “cartesia.ai/sonic”
Techniques: Morph
Camera: Static