Ammaar Reshi

Ammaar Reshi · Launch Video Breakdown: Hook, Pacing & Motion Design

A Wispr Flow-like voice app vibe-coded on Gemini 3.5 Transcribe, with a demo and open-source drop.

AI AgentsLaunchAugust 26, 2026@ammaar
0:00 · The Hook · Real-time Transcription Demo
0:00 / 0:00

Scene-by-scene timeline & spoken transcript

  1. The Hook

    Real-time Transcription Demo

    “Hey, I'm testing Gemini 3.5 transcribe. Let's see it in action. Let's schedule that meeting for 3:00 p.m.”

    On screen
    AUGUST New York 79° 24 Cloudy, Sunny H:85° L:69° Photos and documents were deleted from here and moved to the Trash. Demo 1 note Today New Note 1:21 PM No additional text Hey, I'm testing Gemini 3.5 transcribe. Let's see it in action. August 24, 2026 at 1:21 PM Let's schedule that meeting for 3:00 p.m. Images Movies config.json other
    Camera
    Static wide shot of a macOS desktop, with a picture-in-picture of the presenter in the bottom right. The main focus is on the 'Notes' application.
    Motion
    Seamless real-time text generation within a native application UI, simulating live dictation. A subtle pulsing microphone icon appears at the bottom center during dictation.
  2. Feature Teaser

    Custom Vocabulary Integration

    “So, I'm going to add a custom vocabulary word, AI Studio, to the dictionary. And now, when I say AI Studio, it'll be spelled correctly.”

    On screen
    AUGUST New York 80° 24 Cloudy, Sunny H:85° L:69° Images Movies config.json other Don't show me this again. Send to Trash. Jot Dictionary Add a word or phrase... Gemini hears it as... (optional) History Settings General Dictation Privacy & Storage Advanced About Teach it your words Names, jargon, product terms — add them once, they're spelled right in every dictation. 0 words AI Studio 1 word Import CSV... Export CSV...
    Camera
    The camera remains static, but a new application window ('Jot') slides in from the right, partially overlapping the 'Notes' app. The presenter remains in the bottom right.
    Motion
    Smooth, rapid window transition with a slight blur effect as the 'Jot' app slides into view. Text input within the 'Jot' app is instantaneous, demonstrating the custom vocabulary feature.
  3. Product Reveal

    Intelligent Contextual Correction

    “We need to schedule a call to talk about the latest features on AI Studio.”

    On screen
    AUGUST New York 80° 24 Cloudy, Sunny H:85° L:69° Images Movies config.json other Demo 1 note Today New Note 1:21 PM No additional text Hey, I'm testing Gemini 3.5 tr... 1:35 PM Let's schedule that meeti... Hey, I'm testing Gemini 3.5 transcribe. Let's see it in action. August 24, 2026 at 1:35 PM Let's schedule that meeting for 3:00 p.m. We need to schedule a call to talk about the latest features on AI Studio. Jot History 53 words dictacted 5 dictations 140 avg WPM Search your dictations Today We need to schedule a meeting to talk about AIS. Notes - 1:35PM We need to schedule a call to talk about AIS. Notes - 1:35PM Let's schedule that meeting for 3:00 p.m. Notes - 1:35PM Hey, I'm testing Gemini 3.5 transcribe. Let's see it in action. Notes - 1:35PM
    Camera
    The 'Jot' app slides back to reveal the 'Notes' app fully, then slides back in to show the 'History' tab. The presenter remains in the bottom right.
    Motion
    Fluid horizontal sliding transitions between application views. Text appears instantly, showcasing the app's ability to correct 'AIS' to 'AI Studio' based on the custom vocabulary, highlighting intelligent contextual understanding.
  4. Call to Action

    Build Your Own Transcription App

    “(No spoken dialogue — The audio track features an ambient electronic score with a consistent, driving tempo. Instrumentation includes pizzicato synths, a prominent sub-bass, and subtle 808-style percussion. High-energy audio transitions are marked by risers and sweeps, often culminating in sub-bass drops or impacts, particularly at key demonstration points. The overall sound design is clean and modern, supporting the product launch theme.)”

    On screen
    This section is beyond the provided frames. Based on the duration and context, it would likely feature more demonstrations, possibly a call to action to use the open-source model, and potentially a final branding screen.
    Camera
    This section is beyond the provided frames. It would likely involve continued screen capture, possibly zooming into specific UI elements or showing code snippets.
    Motion
    This section is beyond the provided frames. It would likely continue the pattern of seamless UI interactions, real-time text generation, and potentially incorporate more abstract motion graphics to highlight the underlying AI technology.

Related AI Agents Product Launches

Explore all AI Agents launches →
OpenAI
Hook 9.2137.9M
OpenAIAI Agents

To ensure that artificial general intelligence benefits all of humanity

@OpenAI
Gopuff
Hook 9.277.6M
GopuffAI Agents

Gopuff introduces Go, an AI shopping assistant built with SpaceXAI: say what you need and the order is placed.

@gopuff
Elon Musk
Hook 9.263.3M
Elon MuskAI Agents

Iliad (Troy) trailer made by Grok Imagine 1.5, which was just released

@elonmusk