so i clipped out pauses between dialogue, and sped up the talking speed 10% used cuts/zoom to make these transitions more natural (tip from @crystalwizard
) , and then used canva's auto-caption tool
@yoheinakajima
-
Video editing techniques for AI content creation and automation
By
–
-

ChatGPT and Runway Generate Video Scripts Automatically
By
–
and then for each scene, i used chatgpt to generate the two characters in a different scene, and prompted runway to generate the script. one sentence per character per generation worked pretty well
-
Controlling AI dialogue consistency and speaker attribution challenges
By
–
even on runway, if the dialogue went back and forth too much, it didn't keep consistency on who speaks, and was hard to control
— Yohei (@yoheinakajima) 22 septembre 2025
(example video here messes this up) pic.twitter.com/IMt6vgpyhReven on runway, if the dialogue went back and forth too much, it didn't keep consistency on who speaks, and was hard to control (example video here messes this up)
-
Comparing AI Video Tools for Multi-Person Dialogue Generation
By
–
i then tried a couple of tools to generate the dialogue, but couldn't quite get there with hedra (great for one person, but not two+), multitalk (this model is specifically for this, but i wasn't getting the quality i wanted), grok, sora, gemini, and ended up settling on runway -… pic.twitter.com/LmmOiLVps0
— Yohei (@yoheinakajima) 22 septembre 2025i then tried a couple of tools to generate the dialogue, but couldn't quite get there with hedra (great for one person, but not two+), multitalk (this model is specifically for this, but i wasn't getting the quality i wanted), grok, sora, gemini, and ended up settling on runway –
-

Artist Generates Surreal Car Scene Using AI Image Generation
By
–
this was just an idea at first, i started by generating an image of a unicorn and alien in the back of a car
-
Creating AI-Generated Video Content for $120 Using Runway ML
By
–
for anyone curious about the video…
— Yohei (@yoheinakajima) 22 septembre 2025
took about ~$120 using @runwayml to generate the clips, images by chatgpt, edited in canva
full process 👇 https://t.co/sxxAsnwOkLfor anyone curious about the video… took about ~$120 using @runwayml to generate the clips, images by chatgpt, edited in canva full process
-
HeyGen vs Runway: Multi-character dialogue control tradeoffs
By
–
Heygen seems to give more control over dialogue but it’s too bad you can only do one voice at a time. Runway was able to do a single shot with multiple characters talking, but harder to keep voice consistent across multiple runs
-
Runway ML Selected for Multi-Character Video Generation Quality
By
–
in case anyone's curious, after trying Hedra, MultiTalk, Grok, a custom app on Google AI Studio… i settled on @runwayml for this, which was only one that met the quality i wanted – but could only generate up to one phrase each for the two characters per generation (when i
-
Using MCPs to automate calendar event creation workflows
By
–
someone said they use MCPs to drop calendar events on their cal from this flow, so I clearly have room to upgrade 🙂
-
Well-designed AI tool onboarding experience with account integration
By
–
love the onboarding for this, very well designed!
— Yohei (@yoheinakajima) 9 septembre 2025
excited to try it out, already connected my accounts and invited to slack. let's see how good this memory is 🙂 https://t.co/iQ27XTuoVQlove the onboarding for this, very well designed! excited to try it out, already connected my accounts and invited to slack. let's see how good this memory is 🙂