Subtitle Generation

Quick Start

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this video with accurate timestamps",
    "mode": "max",
    "file_urls": ["https://example.com/my-video.mp4"]
  }'

Subtitle Formats & Outputs

Use Case Examples

1. Auto-Generate Subtitles from Video

Automatically transcribe speech from a video file with accurate word-level timestamps.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transcribe this video and generate subtitles with accurate timestamps. Output as SRT format. The video contains English speech.",
    "mode": "max",
    "file_urls": ["https://example.com/interview-video.mp4"]
  }'

2. Multi-Language Subtitle Generation

Generate subtitles in multiple languages directly from the audio.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this video in English, Spanish, and French. Provide separate SRT files for each language. The original audio is in English.",
    "mode": "max",
    "file_urls": ["https://example.com/product-demo.mp4"]
  }'

3. Animated/Styled Captions (TikTok Style)

Create eye-catching animated captions with word-by-word highlighting, popular on TikTok and Instagram Reels.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Add TikTok-style animated captions to this video. Use bold white text with black outline, word-by-word pop animation, centered at the bottom third of the screen. Make it trendy and engaging.",
    "mode": "max",
    "file_urls": ["https://example.com/short-form-content.mp4"]
  }'

4. SRT/VTT Export

Generate clean subtitle files in standard formats for use in video editors or streaming platforms.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transcribe this video and export subtitles in both SRT and VTT formats. Ensure proper line breaks (max 42 characters per line, 2 lines max). Include timestamps accurate to milliseconds.",
    "mode": "max",
    "file_urls": ["https://example.com/documentary.mp4"]
  }'

5. Speaker Diarization (Identify Speakers)

Generate subtitles that identify and label different speakers in conversations, interviews, or podcasts.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this podcast with speaker diarization. There are 2 speakers - identify them as Speaker 1 and Speaker 2 (or Host and Guest if you can determine roles). Format each line with the speaker label.",
    "mode": "max",
    "file_urls": ["https://example.com/podcast-episode.mp4"]
  }'

6. Subtitle Translation

Translate existing subtitles from one language to another while preserving timing.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Translate these English subtitles to Japanese. Preserve the original timing and format. Ensure natural Japanese phrasing rather than literal translation.",
    "mode": "max",
    "file_urls": ["https://example.com/original-subtitles.srt"]
  }'

7. Burned-In Subtitles

Render subtitles directly into the video file (hardcoded/embedded) so they appear without needing player support.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this video and burn them directly into the video. Use white text with black background box, Arial font, positioned at bottom center. Output a new video file with embedded subtitles.",
    "mode": "max",
    "file_urls": ["https://example.com/social-media-clip.mp4"]
  }'

8. Word-by-Word Karaoke Style

Create karaoke-style subtitles with word-by-word highlighting, perfect for music videos and lyric content.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Create karaoke-style subtitles for this music video. Display lyrics with word-by-word highlighting as they are sung. Use a gradient color change effect (from white to yellow) for the currently sung word. Center the text on screen.",
    "mode": "max",
    "file_urls": ["https://example.com/music-video.mp4"]
  }'

9. Subtitle Timing Adjustment

Fine-tune subtitle timing for better synchronization with audio.

# First, upload video and generate initial subtitles
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this video",
    "mode": "max",
    "session_id": "subtitle-timing-project",
    "file_urls": ["https://example.com/video-with-delay.mp4"]
  }'

# Then adjust timing in the same session
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "The subtitles are appearing 500 milliseconds too early. Shift all subtitle timings forward by 500ms and regenerate the SRT file.",
    "session_id": "subtitle-timing-project"
  }'

10. Batch Subtitle Generation

Generate subtitles for multiple videos in a single workflow.

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate English subtitles for all these videos. Output SRT files for each. Use consistent formatting across all videos: max 2 lines, 42 characters per line, minimum 1 second display time per subtitle.",
    "mode": "max",
    "file_urls": [
      "https://example.com/episode-01.mp4",
      "https://example.com/episode-02.mp4",
      "https://example.com/episode-03.mp4"
    ]
  }'

Best Practices

Transcription Quality

• Clear Audio: Best results with clear speech and minimal background noise
• Language Hint: Specify the source language for better accuracy
• Speaker Count: Mention number of speakers for better diarization
• Context: Provide context about the content (technical terms, names) for accuracy

Subtitle Formatting

• Line Length: Keep lines under 42 characters for readability
• Duration: Each subtitle should display for 1-7 seconds
• Lines Per Subtitle: Maximum 2 lines per subtitle block
• Reading Speed: Target 150-180 words per minute for comfortable reading

Animated Captions

• Font Choice: Bold, sans-serif fonts work best for short-form content
• Contrast: Use outlines or shadows for visibility on any background
• Position: Keep safe zones clear for platform UI elements
• Animation: Subtle animations are more readable than dramatic effects

Translation

• Cultural Adaptation: Request localization, not just translation
• Timing Flexibility: Some languages need more time to read
• Character Limits: CJK languages often need fewer characters per line

Prompt Tips for Subtitle Generation

When requesting subtitles, include these details in your prompt:

1. Source Language: What language is spoken in the video?
2. Target Format: SRT, VTT, burned-in, or animated?
3. Style Requirements: Font, color, position, animation
4. Speaker Info: Number of speakers, roles if known
5. Special Terms: Technical vocabulary, names, brands
6. Output Languages: Single language or multiple translations

Example Prompt Structure

"Generate [format] subtitles for this video.
Source language: [language].
[Number] speakers: [roles if known].
Style: [font, color, position requirements].
Special terms to recognize: [names, technical words].
Additional requirements: [line length, timing, etc.]"

Mode Selection

Ask your users before generating:

"Do you want fast & cheap, or high quality?"

Multi-Turn Subtitle Refinement

Use session_id to iterate on subtitle generation:

# Initial subtitle generation
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this video with speaker identification",
    "session_id": "subtitle-project-001",
    "file_urls": ["https://example.com/interview.mp4"]
  }'

# Refine based on feedback
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change Speaker 1 label to John and Speaker 2 to Sarah. Also fix the spelling of TensorFlow wherever it appears.",
    "session_id": "subtitle-project-001"
  }'

# Add styling and export
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Now create a burned-in version with the corrected subtitles. Use yellow text for John and cyan for Sarah.",
    "session_id": "subtitle-project-001"
  }'

Language Support