alt Hacker NewsThese AI explainers are taking over. I tried getting this working back in May. The models were okay but not quite there and it was a ton of effort. Opus 5.5 seems like the tipping point.
I made an OSS framework for these for when you want to go beyond one-shoting it: https://github.com/scosman/videowright
- Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and timestamp a real voiceover
- can reorder scenes both in code, and using ffmpeg for audio.
- interactive controls during authoring, can ask for micro edits or re-builds
- MP4 export/encoder
- Generates a video from a prompt (obvs)
That video in the README is amazing! Will definitely dig into this project.
We're not using Opus 5.5 btw, as it would be too expensive. Our goals is to eventually get the cost down to 1 cent for a 1 minute video, and with 1 second delay from submit to playback. For that, we need dirt cheap and lightning fast models.