Cartesia

Cartesia · Launch Video Breakdown: Hook, Pacing & Motion Design

The #1 real-time speech and transcription models purpose-built for voice agents. One API, no tradeoffs between quality and speed.

AI AgentsProductionAugust 27, 2026@cartesia
0:00 · The Hook · Office Celebration
0:00 / 0:00

Scene-by-scene timeline & spoken transcript

  1. The Hook

    Office Celebration

    “(No spoken dialogue — upbeat lo-fi hip hop intro beat)”

    On screen
    (No on-screen text)
    Camera
    Static wide and mid-shot cuts in modern office
    Motion
    Fast-paced jump cuts matching beat
  2. Problem Agitation

    Checking the Leaderboard

    “We're number one on the TTS leaderboards. Weren't we already? Yeah, no one beat our last model, so we just topped ourselves. Somebody had to. And... head to head? How far ahead are we?”

    On screen
    (No on-screen text)
    Camera
    Medium over-the-shoulder to frontal two-shot
    Motion
    Naturalistic live-action framing
  3. Product Reveal

    Leaderboard Motion Graphic

    “Let's see... on the provider voice leaderboard, we're over 40 points ahead of the next model.”

    On screen
    1104 1167 1215 1219 1223 1238 1238 1283
    Camera
    Full-screen graphic scroll and scale
    Motion
    2D animated bar chart reveal on green grid
  4. Feature Teaser

    Playful AI Personality

    “And people preferred us over the leading competitor 92% of the time in English. 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.”

    On screen
    (No on-screen text)
    Camera
    Close-up reaction shots
    Motion
    Subtle handheld breathing camera
  5. Feature Teaser

    Multilingual Accent Showcase

    “Hey guys, are you guys talking to Sonic, the new model? Yeah. You want to hear it? Yeah. Hey Sonic, how's your Indian accent? Hey Sonic, how's your Indian accent? Are you mocking me? Sonic-3.6 aa gaya! Sonic-3.5 ke sirf teen mahine baad. Should I do my British accent next? Maybe not. Can you try Spanish? ¡Pero me esforcé tanto con mi acento británico! Does it actually sound natural though? Naturellement. Natürlich. Naturally. Okay, the British accent sounds pretty good, even for me.”

    On screen
    Sonic-3.6 English(US) Hindi(IN) Spanish(ES) French(FR) German(DE) English(UK)
    Camera
    Intercut between screen capture and reaction angles
    Motion
    Upper-left badge pop-ups tracking spoken language/emotion tags
  6. Product Reveal

    Sonic Nails The Launch Read

    “All right, guys. Let's get back to the launch video. Sonic! Let's take it from the top, but this time be super excited! Sonic 3.6 is here. The most natural TTS we've shipped. Native in 44 languages. I match whatever the conversation needs: tone, pacing, emphasis... Just like a coworker would.”

    On screen
    English(US)
    Camera
    Over-the-shoulder onto laptop screen, cut to smiling team
    Motion
    Dynamic waveform visualizer on screen interface
  7. Call to Action

    Title Slate Outro

    “Do you guys ever think we're actually going to get this launch video out? Or is Sonic going to keep bragging to us?”

    On screen
    CARTESIA Sonic-3.6 Now Live
    Camera
    Static graphic overlay atop blurred background footage
    Motion
    Clean typography fade and logo lockup

Related AI Agents Startup Launches

Explore all 1064 AI Agents launches →
OpenAI
Hook 92.0137.9M
OpenAIAI Agents

To ensure that artificial general intelligence benefits all of humanity

@OpenAI
Anthropic
Hook 92.057.6M
AnthropicAI Agents

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available. https://t.co/2AvmEjHIX8

@claudeai
xAI
Hook 9.256.9M
xAIAI Agents

To understand the true nature of the universe.

@bot
Cartesia Launch Video Breakdown: Hook, Pacing & Motion Design | Animatiq