# Auto Caption

Canonical page: https://fuser.studio/models/auto-caption

Auto Caption in Fuser transcribes a video and burns subtitles into it, with font, stroke and position controls. Run it as the last step of a video workflow.

## Specs

| Spec | Value |
| --- | --- |
| Inputs | Video |
| Output | video |
| Cost | 138 credits per run |

Burn synchronized, high-contrast subtitles into video clips with customizable typography and screen placement

[Burn video subtitles](https://app.fuser.studio)

## How Auto Caption works

Convert raw spoken video into captioned, platform-ready content in three quick adjustments.

### Upload source footage

Provide your video file under 400MB containing clear spoken dialogue and audible vocal audio.

### Configure caption styling

Select font, text color, outline stroke width, alignment, and display refresh duration to match your visual branding.

### Export captioned video

Generate your finalized video with synchronized vector text burned directly into the output frames.

## What Auto Caption is good at

Engineered for crisp typography, accurate speech synchronization, and versatile cross-platform styling.

### Automated Speech Transcription

Extracts spoken speech from your video audio track and generates synchronized, frame-accurate subtitles without manual transcription timelines.

### Customizable Typography and Strokes

Select from 32 distinct colors and 5 font families, complete with customizable stroke widths up to 10 pixels to prevent text from blending into bright or dynamic footage.

### Precise Frame Alignment

Lock captions to nine distinct screen coordinates across horizontal and vertical axes to fit perfectly within mobile safe zones and avoid native interface overlays.

### Adjustable Display Durations

Fine-tune caption display duration from 1.0 to 10.0 seconds to match the natural cadence of fast-paced shorts or long-form educational dialogue.

## Made with Auto Caption

Explore captioned video compositions styled across diverse creative genres and aspect ratios.

### Cinematic performance capture with high-contrast centered dialogue

### Industrial design showcase with dynamic lower-third typography

### Vertical creator recipe tutorial styled with bold punchy subtitles

### Editorial lookbook interview framed with elegant serif captions

## What people build with Auto Caption

Discover how creators, brands, and production pipelines automate video accessibility at scale.

### Social Shorts and Reels

Burn bold, high-contrast captions into vertical reels and short-form videos so viewers immediately engage even when audio is muted.

### Commercial Video Ads

Deliver polished, brand-aligned marketing videos with custom colorways and outline strokes that stay legible across diverse ad feeds.

### Documentary and Narrative Storytelling

Pair mini-documentaries, masterclasses, and interviews with timeless serif typography and longer display intervals for relaxed reading.

### Fashion Lookbooks and Interviews

Complement fashion films and lookbook interviews with minimalist typography that honors high-end art direction without visual clutter.

### Programmatic Content Engines

Automate subtitle rendering for high-volume narration pipelines, explainer videos, and programmatic content engines without human intervention.

## Frequently Asked Questions

### What video inputs and file sizes does Auto Caption support?

Auto Caption processes video files containing clear spoken audio with an upload file size limit of up to 400MB. For optimal transcription accuracy, ensure the vocal track is clean and mixed at least 10 to 15 dB louder than any background music or sound effects.

### Can I export standalone subtitle files like SRT or VTT?

No, Auto Caption hardcodes burned-in vector subtitles directly into the output video frames. It produces a finished, rendered video file rather than sidecar caption formats like SRT or VTT.

### What typography and styling options can I customize?

You can choose between five distinct fonts (Standard, Arial, Garamond, Times New Roman, and Georgia), select from 32 text colors, scale font sizes from 1 to 148, and apply an outer stroke width from 1 to 10 pixels to maintain sharp legibility against busy backgrounds.

### How do I adjust subtitle screen placement and display timing?

You can position subtitles across horizontal (left, center, right) and vertical (top, center, bottom) coordinates to fit platform-specific safe zones. Display durations can also be configured from 1 to 10 seconds to match either rapid-fire delivery or relaxed narrative pacing.

### How much does it cost to process a video?

Auto Caption is billed as one flat amount per video run, so a long clip costs the same as a short one.

## Try Auto Caption on Fuser

Burn synchronized, high-contrast subtitles into video clips with customizable typography and screen placement

[Burn video subtitles](https://app.fuser.studio)

## Related models

- [Kling 4.0](https://fuser.studio/models/kling-4-0.md)
- [MiniMax H3 Reframe](https://fuser.studio/models/minimax-h3-reframe.md)
- [Kling 3.0 Video](https://fuser.studio/models/kling-3-0-video.md)
- [MiniMax H3](https://fuser.studio/models/minimax-h3.md)
- [Seedance 2](https://fuser.studio/models/seedance-2.md)
- [Gemini Omni Video](https://fuser.studio/models/gemini-omni-video.md)

Node reference: [Auto Caption docs](https://docs.fuser.studio/docs/nodes/video/auto-caption.md)

## More articles

- [How to Edit a Video With Text Prompts: Kling O3 Edit, Gemini Omni, Grok and Luma Tested](https://fuser.studio/articles/edit-video-with-text-prompts.md)
- [Wan 3.0 vs Seedance 2.5: Same-Input Video Test](https://fuser.studio/articles/wan-3-0-vs-seedance-2-5.md)
- [Wan 3.0 Guide: 30-Second Video, References and Prime](https://fuser.studio/articles/wan-3-0-guide.md)