Bland

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

Speech-to-speech model that listens while it speaks, for noisy phone calls

0:00 · The Hook · Raw Audio Sample Mystery
0:00 / 0:00
AI & MLProductionNovember 13, 2026

Counter-Intuitive Demo / Mystery Hook

5.5

Cuts / min

1:49

Runtime

598K

Views

1,912

Likes

0

Reposts

0

Replies

Scene-by-scene timeline & spoken transcript

  1. The Hook

    Raw Audio Sample Mystery

    “Yeah, we can bring it in on the 5th... Not the 5th, he's talking on the phone... Oh, the 6th. Sorry, the 6th.”

    On screen
    Call recording (10.4 sec) Caller Background speaker Background noise
    Camera
    Static medium shot with lower-third visualizer overlay
    Motion
    Multi-track audio waveform playback visualization
  2. Product Reveal

    Tofu-1 Model Unveil & Human Benchmark

    “The clip you just heard was entirely generated by AI. The man, the woman, the background noise, all of it. It's part of Tofu, our new speech-to-speech model that's coming in early January. 92% of people interacting with Tofu couldn't tell it was AI.”

    On screen
    Speech-to-Speech Model Tofu-1 Early January 2025 Tofu-1 listening tests 92% couldn't tell it was AI
    Camera
    Static locked-off shot of founder talking to camera
    Motion
    Pop-in metric card and 10x10 dot matrix grid fill animation
  3. Feature Teaser

    Full Duplex & Multi-Speaker Separation

    “It's capable of generating complex soundscapes with background noise, multiple speakers, but also understanding audio as a full duplex model. That means it can hear the difference between a TV and a speaker, understand multiple speakers in a room, or even context of what you're saying. The cocktail effect has been a long problem for voice AI, and Tofu solves that.”

    On screen
    Full duplex audio Agent Caller Room TV Kid Dog
    Camera
    Full-screen graphic sequence returning to founder shot
    Motion
    Multi-channel live audio timeline with synchronized scrolling waveforms
  4. Feature Teaser

    Thinking While Talking Demonstration

    “Okay, um, let me go through these. So, one's already been delivered so I can't cancel that one, and the other one's already canceled. Let's see what's left. Okay, so the makeup kit's still pending, and um...”

    On screen
    Thinking while talking Look up orders Order 1: delivered Order 2: canceled Search open orders Pending
    Camera
    Split layout: founder inset left, synchronized task checklist right
    Motion
    Dynamic bullet list state transitions with live text narration
  5. Problem Agitation

    Voice Paradigm Shift

    “That was another example of our model. You can hear it thinking through a problem where it's able to in real time narrate to a user while taking complex actions on the user's behalf. What we're excited about is that this is a turning point for the entirety of voice. We believe that we've crossed the threshold into complete human naturalness...”

    On screen
    Tofu-1 research preview Join the waitlist
    Camera
    Medium shot on founder with corner CTA badge entrance
    Motion
    Smooth badge reveal with hover-state arrow cue
  6. Call to Action

    Logo Outro & Research Waitlist

    “(No spoken dialogue — subtle ambient tone)”

    On screen
    bland Voice AI for high-stakes calls Join the research preview
    Camera
    Static centered typographic card
    Motion
    Split-bar deconstruction revealing geometric brand mark

Related AI & ML Product Launches

Explore all AI & ML launches →
Grok Bot 1.0 — AI teammates for your team
@bot
AI & ML
@bot
Grok Bot 1.0 — AI teammates for your team@bot
Tauvus
@tavus
AI & ML
@tavus
Tauvus@tavus
Fish Audio
@FishAudio
AI & ML
@FishAudio
Fish Audio@FishAudio