Auto-Subtitle Node

Automatically add subtitles to videos with AI speech recognition.

Overview

The Auto-Subtitle node transcribes speech in videos and adds synchronized subtitles. Perfect for accessibility and social media content.

Inputs

Video File (required)

Video with spoken audio
Clear speech preferred

Outputs

Video with Subtitles

Subtitles burned into video
Or separate SRT file
Synchronized to speech

Configuration

Language

Auto-detect (default)
Or specify language
50+ languages supported

Subtitle Style

Position:

Bottom (default)
Top
Custom

Font:

Size
Family
Color
Background

Format:

Single line
Two lines
Word-by-word

Use Cases

Social Media

Video → Add subtitles → Platform-ready

Accessibility

Make content accessible to deaf/hard of hearing

Foreign Language

Transcribe and translate content

Tutorials

Auto-caption instructional videos

Workflow Integration

Input from:

Image-to-Video
Text-to-Video
Voice-Over Node
Asset Node

Output to:

Export/download
Further editing
Timeline Editor

Languages Supported

English
Spanish
French
German
Chinese
Japanese
And 50+ more

Subtitle Styling

Text Style

Font: Sans-serif, Serif, Mono
Size: Small, Medium, Large
Weight: Regular, Bold
Color: Any color

Background

Solid box
Transparent
Shadow only
Outline

Positioning

Top, middle, bottom
Left, center, right
Custom coordinates

Accuracy

Factors affecting accuracy:

Audio quality
Speaker clarity
Background noise
Accent/dialect
Technical terms

Tips for better accuracy:

Clear audio
Minimal background noise
Standard speech pace
Good microphone

Processing Time

5-second video: ~30 seconds
30-second video: ~1-2 minutes
Depends on speech amount

Editing Subtitles

Auto-Generated

AI transcribes automatically
Usually 90-95% accurate
May need manual review

Manual Corrections

Edit in Timeline Editor
Or download SRT to edit
Re-import corrected file

Export Options

Burned-In:

Subtitles part of video
Can't be removed
Universal compatibility

Separate SRT:

External subtitle file
Can be edited
Player-dependent display

Troubleshooting

Inaccurate transcription:

Check audio quality
Specify language manually
Review and edit manually

Subtitles out of sync:

Regenerate subtitles
Check original audio quality
Manual timing adjustment

Missing words:

Audio unclear at those points
Background noise
Manual addition needed

Wrong language detected:

Specify language manually
Check audio contains speech
Verify language supported

Best Practices

For Social Media:

Large, bold fonts
High contrast
Bottom positioning
Short phrases per subtitle

For Accessibility:

Standard font
Clear background
Speaker identification
Sound effect notation

For YouTube:

Generate SRT file
Upload separately
YouTube player controls
Multiple language support

Cost & Usage

Counts toward audio processing:

Based on video duration
~$0.01-$0.05 per minute with overage

View pricing →