Cartesia - Sonic-3.6 is now generally available. In January we made a bet: stop

01 · Hook · 0:00–0:00

A wide static shot of a sunlit office: a woman with headphones and a man in a checkered shirt type on laptops at a round table, while a third man stands beside a whiteboard. Potted plants and a frosted window frame the background.

Camera: Static

02 · Hook · 0:00–0:01

A young man in headphones sits at a round table working on a laptop in a bright office with plants and a whiteboard. A woman walks past on the right holding a phone to her ear.

Camera: Static

03 · Hook · 0:01–0:01

In a bright office, a man in a plaid shirt sits at a round table working on a laptop while a woman in a dark top leans toward him. A third man stands at a whiteboard covered in hand-drawn diagrams and arrows.

Camera: Static

04 · Hook · 0:01–0:02

Three colleagues sit around a round table in a bright office. A man in a checkered shirt points at a hand-drawn diagram on a whiteboard while a woman types on a laptop and a third man listens.

Camera: Static

05 · Hook · 0:02–0:03

Three people sit around a round white table in a bright office, a laptop open in front of them. They smile and raise their fists for a celebratory bump while a whiteboard with hand-drawn diagrams hangs behind.

Camera: Static

06 · Social proof · 0:03–0:04

Two men in plaid shirts walk in from the right carrying a closed dark laptop and set it on a round white table in a plant-filled studio. One bends to position it while the other follows behind.

Camera: Static

07 · Social proof · 0:04–0:08

In a bright office with a large window and potted plant, a man in a gray t-shirt leans over a seated colleague in a plaid shirt who works on a laptop. White subtitles of their exchange appear at the bottom as the camera holds a medium shot.

On-screen text: “We're number one on the”, “TTS leaderboards.”, “Weren't we already?”

Camera: Pan

08 · Social proof · 0:08–0:10

Two men sit at a round white table with an open laptop; the man in the checkered shirt gestures and talks, then leans back, while the other watches the screen. Potted plants and a window fill the bright room. Dialogue subtitles appear at the bottom.

On-screen text: “Weren't we already?”, “Yeah,”, “no one beat our last model,”

Camera: Static

09 · Social proof · 0:10–0:13

A young man in a gray t-shirt sits in a sunlit office, head tilted down with a grimace, while a second man in a plaid shirt is framed at the right edge. The locked-off shot holds steady as bottom subtitles cycle through his line.

On-screen text: “no one beat our last model,”, “so we just topped ourselves.”, “Somebody had to.”

Camera: Static

10 · Social proof · 0:13–0:16

A man in a blue plaid shirt stands in profile in a bright, plant-filled office, talking to a colleague just out of frame. The locked-off medium close-up holds on his face as he speaks, with white subtitles in a dark box along the bottom.

On-screen text: “Somebody had to.”, “And...head to head?”, “How far ahead are we?”, “Let's see... on the provider”

Camera: Static

11 · Social proof · 0:16–0:21

On a dark green grid, a bar chart builds column by column, each bar rising with a small logo on top and a score at its base. The tallest, a white bar with a green asterisk, stands out over the green bars as captions swap below.

On-screen text: “Let's see... on the provider”, “voice leaderboard,”, “we're over 40 points”, “ahead of the next model.”, “And people preferred us over”

Camera: Pull out

12 · Social proof · 0:21–0:26

Two men sit at a round table in a plant-filled room; the left man faces a dark laptop while the right man watches him. Subtitles caption the bottom of the locked-off frame as they talk.

On-screen text: “And people preferred us over”, “the leading competitor”, “92% of the time in English.”, “I try to think of the other 8 as”

Camera: Static

13 · Social proof · 0:26–0:33

Two men sit side by side in a plant-filled office, watching something off-camera. The man in the plaid shirt smiles and laughs while the man in the grey t-shirt smirks. White subtitles sit at the bottom of the locked-off frame.

On-screen text: “I try to think of the other 8 as”, “motivation.”, “You don't need to sound”, “so smug about it.”, “I am a little smug about it.”

Camera: Static

14 · Product intro · 0:33–0:34

Two men sit side by side in a bright office, the one in a blue plaid shirt smiling toward his companion in a grey tee, with a leafy plant and a frosted window behind them in a locked-off medium shot.

On-screen text: “I am a little smug about it.”

Camera: Static

15 · Product intro · 0:34–0:35

Two men sit at a white round table with a laptop in a plant-filled room, one in a brown tee, one in a checkered shirt. They turn to look at each other as a woman walks in from the right. Subtitle captions appear centered at the bottom.

On-screen text: “Hey guys,”, “are you guys talking to Sonic,”

Camera: Static

16 · Product intro · 0:35–0:36

A woman in a navy sleeveless top walks across a bright, plant-filled office holding a plastic cup with a dark drink and straw. Out-of-focus colleagues sit in the foreground. Subtitles caption her line at the bottom.

On-screen text: “are you guys talking to Sonic,”, “the new model?”

Camera: Pan

17 · Product intro · 0:36–0:38

Locked-off over-the-shoulder shot past a blurred head onto a laptop screen. On a teal canvas, the white label Sonic-3.6 types out letter by letter above a hand-drawn arrow pointing to a green pinwheel mark; small white serif subtitles carry the dialogue at the bottom.

On-screen text: “the new model?”, “Yeah. You want to hear it?”, “Hey Sonic,”

Techniques: Kinetic type

Camera: Static

18 · Feature reveal · 0:38–0:40

Three people sit around a round white table in a bright room with potted plants, a laptop open on the table. Locked-off medium shot; the man on the right speaks while the other two listen, and white subtitles appear at the bottom center.

On-screen text: “Sonic-3.6”, “Hey Sonic,”, “how's your Indian accent?”

Camera: Static

19 · Feature reveal · 0:40–0:43

Over-the-shoulder shot of an open laptop on a white desk; its screen shows a teal video-call view with a green pinwheel logo centered. A dark blurred shoulder fills the right foreground, the office background stays out of focus. White serif subtitles swap at the bottom of the frame.

On-screen text: “how's your Indian accent?”, “HEy SOnIc,”, “hoW's yOur INdiAn aCcEnt?”

Camera: Static

20 · Feature reveal · 0:43–0:45

Three people sit at a round table with an open laptop. A corner chip shows English(US) while the bottom caption reads Are you mocking me?. The chip flips to Hindi(IN) and the caption switches to a Hindi line, then the shot cuts to a close-up of the woman's shoulder.

On-screen text: “How's your Indian accent?”, “English(US)”, “Are you mocking me?”, “Hindi(IN)”, “Sonic-3.6 आ गया!”, “[Sonic-3.6 is here]”

Camera: Static

21 · Feature reveal · 0:45–0:47

Close-up of a smiling woman in a navy polo, then a cut to a wide shot of three people around a round white table with a laptop, plants behind. A language tag sits top left; bilingual subtitles run along the bottom.

On-screen text: “Hindi (IN)”, “Sonic-3.6 आ गया!”, “[Sonic-3.6 is here]”, “Sonic-3.5 के सिर्फ़ तीन महीने बाद।”, “[3 months after Sonic-3.5]”

Camera: Pull out

22 · Feature reveal · 0:47–0:53

Three people sit around a round white table with a laptop and a drink, in a bright plant-filled room. The woman on the left gestures at the laptop as the man on the right talks. A language badge and bottom subtitles stay fixed on a locked-off frame.

On-screen text: “Hindi (IN)”, “Sonic-3.5 के सिर्फ़ तीन महीने बाद।”, “[3 months after Sonic-3.5]”, “Should I do my British accent next?”, “Maybe not.”, “Can you try Spanish?”

Camera: Static

23 · Feature reveal · 0:53–0:57

Over-the-shoulder close-up of a laptop showing a teal video-call screen with a green pinwheel logo and a purple participant tile, a blurred head at the right edge. A white pill with an angry emoji swaps from Hindi to Spanish while bilingual subtitles change.

On-screen text: “Hindi (IN)”, “Can you try Spanish?”, “Spanish (ES)”, “¡Pero me esforcé tanto con [But I worked so hard]”, “mi acento británico! [on my British accent]”, “Does it actually sound”

Camera: Static

24 · Feature reveal · 0:57–1:00

Two men sit in a bright room with plants behind them. The man in the plaid shirt on the right talks while the man in the dark tee on the left looks down. A top-left badge swaps from Spanish to French to German as the bottom subtitles change.

On-screen text: “Spanish (ES)”, “Does it actually sound”, “natural though?”, “French (FR)”, “Naturellement.”, “German (DE)”, “Natürlich.”

Camera: Pan

25 · Feature reveal · 1:00–1:03

Three people sit around a round table in a bright, plant-filled room, a laptop facing away. A white chip top-left switches language tags beside a smiley emoji, while bottom serif subtitles change from 'Natürlich.' to 'Naturally.' and 'Okay, the British accent sounds pretty good.'

On-screen text: “French(FR)”, “Natürlich.”, “German(DE)”, “Naturally.”, “English(US)”, “Okay, the British accent”, “sounds pretty good,”

Camera: Static

26 · Demo · 1:03–1:11

A woman in a navy blouse smiles at a laptop, then the frame pans right to a man in a grey t-shirt who talks, a second person at the edge. White subtitles sit at the bottom; a small English (UK) tag with a smiley emoji stays top-left.

On-screen text: “even for me.”, “All right, guys,”, “let's get back”, “to the launch video.”, “Sonic!”, “Let's take it from the top.”, “be super excited!”, “Sonic 3.6 is here,”

Camera: Pan

27 · Demo · 1:11–1:15

Over-the-shoulder live shot of a person facing a laptop on a white table; the screen shows a teal canvas with a glowing green logo inside a browser window. The top-left language tag flips from UK to US as bottom subtitles cycle through the announcement. Camera stays locked off.

On-screen text: “English (UK)”, “Sonic 3.6 is here.”, “English (US)”, “The most natural”, “TTS we've shipped.”

Camera: Static

28 · Demo · 1:15–1:17

Two men sit in a bright office; the one in a plaid shirt laughs in profile while his companion looks down. A white caption 'Native in 44 languages.' sits at bottom center, a small 'English (US)' chip with a sun icon rests top left. The frame is locked off.

On-screen text: “TTS we've shipped.”, “Native in 44 languages.”

Camera: Static

29 · Demo · 1:17–1:23

Three people sit around a round white table with a closed dark laptop, smiling and exchanging glances. White serif subtitles roll across the bottom while a small language badge holds in the top-left. The camera stays locked off.

On-screen text: “English (US)”, “Native in 44 languages.”, “I match”, “whatever the conversation”, “needs.”, “Tone,”, “pacing, emphasis.”, “Just like a coworker would.”

Camera: Static

30 · Outro · 1:23–1:31

Locked-off, heavily blurred office shot: people sit at a table while one stands at a whiteboard. Centered over it, the green CARTESIA mark with “CARTESIA”, “Sonic-3.6”, “Now Live” stays static, and bottom captions swap line by line to match the voiceover.

On-screen text: “CARTESIA”, “Sonic-3.6”, “Now Live”, “Just like a coworker would.”, “Do you guys ever think”, “we're actually gonna get this”, “launch video out?”, “Or is Sonic”, “gonna keep bragging to us?”

Camera: Static