# Horizontal to Vertical Video

Landscape to 9:16 for Shorts, TikTok, and Reels, following whoever's talking.

## How it works

1. Add your landscape video and pick where it's going: TikTok, Reels, Shorts, or a square post.
2. Press Reframe. Audo follows whoever's talking; drag a crop or change a shot's layout to fix it.
3. Play the vertical result right on the page, then export the MP4.

## How auto reframe keeps the speaker in frame

Audo's horizontal to vertical video converter works shot by shot. It finds each camera cut, looks for the faces in every shot, and when the video has speech, matches each voice to the face that's talking. The frame then follows that person, easing between positions instead of jumping, and holds still while they barely move.

What you get first is a plan you can see and change: each shot's layout, crop, and keyframes. The preview on this page is drawn from that plan frame by frame, the way the finished MP4 is made, so what you watch is what you export. It's a 16:9 to 9:16 converter, and a vertical video converter for square and 4:5 posts too; it also turns a tall video into 16:9 for YouTube.

The sound is copied from your original, unchanged. A silent video works too: Audo follows the biggest face instead. People talking over each other, someone speaking off camera, or a fast turn of the head can fool it, and that's what the editor is for.

Tool: Reframe video (`reframe_video`). Price: 3 credits a minute — $0.03/min ($1.80/hr), with no subscription — of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@clip.mp4 -F ratio=9:16 https://audo.ai/api/try/reframe-video -D response.headers -o response.body
```

Read response.headers and response.body before naming media. Handle 202, 200 JSON and errors with the complete response client at https://audo.ai/docs/api?utm_source=markdown&utm_medium=agent#responses.

Free for the first 2 minutes of each file, 3 times a day per person, with no key or account. Uploads up to 10 GB, 2 at once from one address. The response is the result itself; a job that runs longer than about 30 seconds returns 202 with a link to check on it. With an API key (`-H "Authorization: Bearer $AUDO_API_KEY"`), omitting free runs the whole file with credits if the balance covers it, otherwise the free portion if quota remains. Set free=true to prohibit spending; for paid whole files use free=false with an approved positive max_credits. A free result cut short comes with finishUrl (and the Audo-Finish-Url header when the response is the file itself): give it to the person, who pays there (from $5, no sign-up), and the whole file runs; keep checking the status link, whose finishedBy names the whole-file job and its own status link. Details: https://audo.ai/docs/api.md

## Options

Form fields with the same names as the MCP tool's inputs:

- `ratio`: Output ratio. Default 9:16.
- `output`: Explicit even pixel dimensions and ratio; overrides ratio.
- `layout`: Default layout for detected scenes. Every panel remains editable in the returned plan.
- `settings`: Tracking settings: subject, smoothing 0 to 1, min_switch_ms, snap_to_center, scene_detection and scene_threshold 0 to 100.
- `background`: Padding behind panels: blur or solid color, hex color, and blur strength.
- `pinned_speaker`: Keep this speaker when speaker turns can associate them with a face.
- `speaker_turns`: Optional existing diarize turns in milliseconds. Otherwise active_speaker requests speaker labels when available.
- `plan_file_id`: 
- `plan`: Edited v1 plan: skips analysis and renders its paths, placements, backgrounds and easings exactly. Costs 1 credit/min instead of 3.

## Languages

Any language: it works on the sound, not the words.

## From an assistant (MCP)

Add https://audo.ai/mcp and sign in (setup for each assistant: https://audo.ai/setup.md). The tool is `reframe_video`:

> Reframes video to 9:16, 1:1, 4:5 or 16:9, following faces across scenes. Layouts: fill, fit with blur or color, split, three, four, screen_facecam and pip. Every crop, placement and eased keyframe is editable in ReframePlan v1. Supply plan or plan_file_id to skip analysis and render exactly that document. Keeps the soundtrack. It costs 3 credits a minute including analysis, or 1 with a supplied plan, charged only if the job succeeds. Free for the first 2 minutes, 3 times a day. Returns MP4 and the plan JSON, or job_id for get_job if it takes longer.

Example: "Use Audo to reframe clip.mp4 to 9:16 for TikTok, following whoever is talking."

## Questions

**How do I convert a horizontal video to vertical?** Add the video above, choose TikTok, Reels, or Shorts, and press Reframe. Audo finds the camera cuts and the person talking in each shot, then plays the 9:16 result beside your original. Fix any shot you like, then press Export video for the MP4. Your sound stays exactly as it was.

**What's the difference between 16:9 and 9:16?** They're one shape turned on its side. 16:9 is wide, as YouTube, TVs, and most cameras record; 9:16 is a tall phone screen, as Shorts, TikTok, and Reels fill it. Going from 16:9 to 9:16 keeps about a third of the width, so what matters is which third. That's the part Audo's auto reframe picks for you, shot by shot.

**Does auto reframe follow the person talking?** Yes. In each shot, Audo picks the face of whoever is speaking and moves the frame with them, smoothly, without jumping at every glance. You can have it follow the biggest face instead, keep the middle, or frame it by hand. Under Camera, choose how steady the movement is and how long it stays on one person before switching.

**Can I fix a shot it got wrong?** Every shot can be changed. Drag the crop window on your original to move it: a change at one moment becomes a keyframe, and the frame eases from one keyframe to the next. Hold still pins a shot in place, Split here cuts a shot in two so each half gets its own framing, and Undo takes back any change.

**What about two people, or a screen recording?** Give each shot a layout. Split stacks two people, one above the other, and Three and Four stack more. Screen + face puts a screen share above the presenter's face, and Face in corner keeps the whole picture with a face inset. Fit shows the whole frame on a blurred or colored background, for shots where nothing should be cut off.

**Can I turn a YouTube video into Shorts or a TikTok?** Start from a video file you made or have permission to use: Audo takes files, not YouTube links. Reframe it to 9:16 here, then cut it down to the moment you want and add captions before you post. Audo works on the whole video, so one long recording can become several vertical clips.

**Is it free?** Yes. Audo reframes the first 2 minutes of a video free, 3 times a day, without an account. A whole video costs $0.03 a minute ($1.80 an hour) to reframe in one go, or $0.01 a minute to frame and $0.01 a minute to export your edit, charged only when it works. No subscription. See pricing.

## More

- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/horizontal-to-vertical-video?utm_source=markdown&utm_medium=agent