8 articles about ai-video.
gemini-omni-flash-preview was deprecated September 30, 2026. Swap to gemini-omni-1.1-flash in n8n, Make or curl, then reframe the 1080p output to 9:16.
TikTok's AI generated label isn't automatic: set it with is_aigc in the Direct Post call, then burn a visible disclosure that survives your re-encode.
The Sora API shutdown alternative for n8n: swap in an async Veo 3.1 or Kling 3.0 call, then normalize the output with reframe, concat, captions and audio mix.
Extract last frame FFmpeg commands return the wrong frame after a fast seek. Use -sseof with -update 1, then join Veo 3 and Sora 2 clips with no seam.
Veo and Sora render only 16:9 and 9:16. Get the AI video aspect ratio math and FFmpeg crops that turn one 9:16 generation into 4:5, 1:1, and 16:9 files.
AI avatar video automation stalls after the talking head renders. The assembly chain: stitch b-roll, burn captions, add a music bed, and ship 9:16 vertical.
The AI video generator workflow nobody documents: extract last frames, normalize mismatched clips, concat, lay an audio bed, burn captions once with FFmpeg.
The fal ai ffmpeg api covers compose and merge-videos at $0.0002/second. Where that fits an AI video pipeline, and where a full FFmpeg surface wins out.