←
Craig Watson5,320 posts
Craig Watson avatar

Craig Watson

@cdcwatson

70% serious, 35% messer | ex @spotify @intercom | vp product @synthesiaIO | I like building and creating with 🅐🅘

◷ Joined February 2009▧ 550 Photos and videos
Aizelsky avatar
⟳ Craig Watson retweeted
Aizelsky@aizelskystudio·Nov 4

What if you're just a delivery guy and something about the order feels off Extra Radish Ep1 - Crime Kdrama style created with seedance 2.5 & gpt image inside @TapNow_AI

3:29
CGBEAST avatar
⟳ Craig Watson retweeted
CGBEAST@Boluwatifeolad7·Nov 10

More Than Gold We follow the story of a reckless young thief and his clever monkey Pico escaping a coastal bazaar with a stolen relic—The kingdoms' worth of treasure piled inside their ship isn't for wealth, but keys to reaching one uncharted void at the edge of the world.

0:45
VIKTHOR ⚡️ avatar
⟳ Craig Watson retweeted
VIKTHOR ⚡️@vikthors_·Nov 9

🔥 THE HANDS OF WAR | Official AI Movie Trailer Two brothers. Two ancient weapons. A forgotten war between humanity and the gods. And something far worse is awakening. Would you watch this movie? ⚔️ Created for the AKOOL AI Film Challenge - COMING NEVER. @AkoolInc #AKOOLClash #AKOOLFilmChallenge #AIVideo #AIFilm

1:30
Craig Watson avatar
Craig Watson@cdcwatson·Nov 2

Everyone on my feed was sharing the Commanding Heights essay last week. 100+ pages. ~40,000 words. I don't have the time to read that. So I turned it into a 14-minute video instead. It covers the core argument, the key turns and the evidence. All in a format I could finish over a coffee. It got me thinking about how much good long-form thinking goes unread because the format is the barrier, not the ideas: reports, strategy papers, research that people bookmark and never open. Anyway, here's the result if you’ve been meaning to read it too 👇

14:04
CGBEAST avatar
⟳ Craig Watson retweeted
CGBEAST@Boluwatifeolad7·Oct 19

Part 3 The story continues. 🔥 Fun fact, I don't know where it's going. Making it up as i go.

0:52

Part 2. This is slowly becoming a story. Made in @invideoOfficial Generated with Seedance 2.5 480p & upscaled to 1080p with Topaz Astra. #aifilm #aifilmmaking

0:55
Synthesia 🎥 avatar
⟳ Craig Watson retweeted
Synthesia 🎥@synthesiaIO·Oct 1

Introducing Sessions: Interactive Avatars that coach, interview, and guide 🗣️ That means you can finally: ✔️ Have 1:1s with your entire company. ✔️ Interview 100 customers a day. ✔️ Train 1,000 sales reps at once. Think of it as a video call, but on the other side is an Avatar that asks, listens, pushes back, and gathers insights. Roleplay Sessions for practice. Survey Sessions for gathering insights. More Sessions coming soon. Explore Sessions today: synthesia.io/sessions

1:33
Jay Nwabueze avatar
⟳ Craig Watson retweeted
Jay Nwabueze@jaynwabueze·Sep 19

We have 12 videos to deliver this weekend. Lol. There's always joy in bringing ideas to life. It feels like you're in motion, and it gives you purpose.

AI Videos Arg avatar
⟳ Craig Watson retweeted
AI Videos Arg@AiVideosArg·Sep 11

Seika's Journey:

1:16
Jay Nwabueze avatar
⟳ Craig Watson retweeted
Jay Nwabueze@jaynwabueze·Sep 7

The current AI race This is so true, I’m hoping Gemini will make a great come back

0:31
VIKTHOR ⚡️ avatar
⟳ Craig Watson retweeted
VIKTHOR ⚡️@vikthors_·Aug 6

Peace is a luxury only few can afford or keep. You think he got him? 🙃 Made with Style and Image: MidJourney Video: Seedance 2.0

0:27
Jay Nwabueze avatar
⟳ Craig Watson retweeted
Jay Nwabueze@jaynwabueze·Sep 2

I get asked this almost every time now. How do your AI videos sound African? The answer is annoying, free, and takes about two minutes to set up. But first, let me name the actual problem, because I don't think enough people are saying it out loud. The visual side has come a long way. Characters look African now. Skin tones read correctly, features are right, wardrobe is believable. Two years ago that was a fight. The voices have not caught up. Not close. Go to ElevenLabs right now and search for Nigerian voices. What you'll find, mostly, are UK-based voice actors with Nigerian nationality. Technically Nigerian. They do not sound like anyone I know. There's no accent in there, or there's a version of the accent that has been sanded down for a British ear. That gap tells you exactly what data these models were trained on, and it wasn't ours. Here's why it matters more than people think. A Nigerian audience will forgive a slightly wrong shot. They will not forgive a wrong voice. The moment a character opens their mouth and sounds like a BBC presenter doing an impression, the whole thing collapses. You lose them in one second, and you don't get them back. So this is how I've been getting around it. I've been testing this in Seedance 2.0 and 2.5. The first part is the one that actually does the work. I use real voices. If I need a specific kind of voice for a project, I go to someone I know who has that voice, and I ask them to record it. Five to fifteen seconds is enough. I explain clearly what it's for, that it's an AI project, and I get their consent before anything else happens. That part is not optional, and it's not just an ethics thing. If the work is commercial, you need to be able to say where that voice came from. Then I save that recording as a voice reference and feed it into the generation. The second part is smaller, but it matters. When I write the prompt, I specify the accent explicitly. Not "he speaks." I write "Nigerian-accented English." If you leave accent out, the model defaults to American. Every time. It has no reason to guess otherwise, because that's the middle of its training data. You have to state it. I want to be clear that the prompt line alone won't save you. I've tested that. Writing "Nigerian accent" with no reference gives you something vague and often embarrassing. The reference audio is doing the heavy lifting. The prompt is just making sure the model doesn't drift away from it. A few things I've picked up doing this. Record clean. A quiet room and a phone is fine. Background noise gets baked in, and you'll hear it in every generation afterwards. Have them speak naturally rather than performing. A normal conversational read carries the accent more honestly than someone putting on their announcer voice. Match the energy to the scene. If the character is angry in your film, a calm reference will fight you the whole way. And keep a library. I've started saving references the same way I save character sheets and wardrobe. Different voices, different registers, all labelled and filed with the consent on record. Once you have five or six good ones, you stop starting from zero on every project. Here's the broader thing I keep coming back to. Nobody is coming to fix this for us. These models get trained on whatever data is easiest to gather, and our voices are not in that pile. Waiting for ElevenLabs to add a proper Lagos accent is not a strategy. The workaround is the work right now. And the creatives who build their own reference libraries are going to have something no model release can hand to anyone else. If you've found a different method that works, I genuinely want to hear it. This is the part of the pipeline I'm still least happy with.

This video is 100% AI I made this for GLOSS AND EXTRA. You can send me a dm to get yours

0:28
VERT avatar
⟳ Craig Watson retweeted
VERT@vert_ink·Aug 23

“THE BLINDERS” Art of smoking.. Craate in @movoai

0:28