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
@yoheinakajima
-
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 🙂
-
April Fools AI Product Moving Toward Reality
By
–
this april fools product is getting closer to reality
-
Using Gemini and Grok for Video Content Creation
By
–
i used Gemini for first video and grok for the second
-
Veo3 and Grok Imagine: Generative AI Video Models Comparison
By
–
correction: it’s apparently veo3, not nano banana – i used gemini the second video uses grok imagine
-
Generate Videos from Images with AI Description
By
–
you can just upload an image and describe the video you want based on it