One still image, one audio file, one bash script → a Ken Burns zoom video with the narration muxed in and auto-generated captions burned on screen. All through the FFmpeg Micro API.

No brew install ffmpeg. No Whisper Docker image. No Python ML stack. Just bash + curl + python3(all preinstalled on macOS and Linux) and a free API key.

What You'll Learn

• ✅ Presigned-URL uploads — push bytes directly to GCS, no egress through our API
• ✅ The /v1/transcribe endpoint — Whisper-powered SRT generation without hosting Whisper yourself
• ✅ Chaining transcribe → transcode — the signed SRT URL drops straight into an FFmpeg subtitles= filter
• ✅ Ken Burns zoom via zoompan — a still image becomes a moving video without a render farm
• ✅ Audio mux with -shortest — keep the video as long as the voice, no manual trimming

How the Script Works

One run of the script performs a six-step pipeline end-to-end:

1. Upload the image — POST /v1/upload/presigned-url + PUT + POST /v1/upload/confirm
2. Upload the audio — same flow, and the confirm response hands back the audio duration so the script knows how long to zoom for
3. Transcribe — POST /v1/transcribe with the audio's gs:// URL, then poll until complete
4. Fetch the signed SRT URL — GET /v1/transcribe/:id/download returns an HTTPS URL good for 10 minutes
5. Render the final video — POST /v1/transcodes with one filter graph: zoompan + subtitles='<signed-url>', and audio mapped from the second input with -shortest
6. Download the MP4 — GET /v1/transcodes/:id/download → curl the signed URL to disk

The whole pipeline is three API calls (transcribe, transcode, download) plus a pair of uploads. Whisper runs on our side, FFmpeg runs on our side, you never install either.

What You'll Need

Cost Breakdown

Video processing minutes are billed per transcode job, rounded up — a 30-second clip consumes 1 billable minute, a 61-second clip consumes 2. Every clip in this pipeline is one transcode, so plan sizing scales directly with how many videos you render.

• • Free plan ($0/mo, 100 min): roughly 100 clips/month at ≤60s each
• • Starter plan ($19/mo, 2,000 min): roughly 2,000 clips/month
• • Pro plan ($89/mo, 12,000 min): roughly 12,000 clips/month

Check FFmpeg Micro pricing for the latest plan limits and features.

Run It — with sample assets (fastest)

The zip also ships a fetch-demo-assets.sh that pulls a sample image + narration from ffmpeg-micro.com/samples — so you can watch the pipeline run end-to-end before curating your own content:

export FFMPEG_MICRO_API_KEY=sk_live_xxx
./fetch-demo-assets.sh
./zoom-and-captions.sh sample-image.jpg sample-narration.mp3 demo.mp4
open demo.mp4

Run It — with your own content

export FFMPEG_MICRO_API_KEY=sk_live_xxx
./zoom-and-captions.sh my-photo.jpg narration.mp3 output.mp4

Come back in ~60 seconds and output.mp4 is a 1280×720 H.264 + AAC file with your image slowly zooming, your voice playing, and captions crawling along the bottom in sync.

Tweaks

The script is short and readable — open it in your editor. Easy knobs:

• • Zoom speed: the zoom+0.0005 increment per frame — lower = slower zoom
• • Max zoom level: the min(zoom+..., 1.3) cap — raise for more dramatic end
• • Caption position: force_style='Alignment=2' — 2 = bottom center, 8 = top center, 1/3 = corners
• • Output resolution: s=1280x720 in the filter — swap to 720x1280 for vertical Shorts / Reels / TikTok
• • Caption font size: Fontsize=22 — raise for more readable captions on mobile

Related training

• • Watermark a video with a logo — same bash + FFmpeg Micro shape, different filter (overlay instead of zoompan + subtitles)
• • Make 100 shorts in under a minute — parallel bash pipeline driven by a CSV

Related endpoints

See the FFmpeg API documentation for the full surface this script uses. Key endpoints:

• • POST /v1/upload/presigned-url — generate signed PUT URLs for direct-to-GCS uploads
• • POST /v1/transcribe — Whisper-powered audio → SRT
• • GET /v1/transcribe/:id/download — signed URL for the generated SRT
• • POST /v1/transcodes — multi-input FFmpeg pipeline with zoompan + subtitles filters