veed/subtitles
Input
Hint: Drag and drop video files from your computer, video from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp4, mov, webm, m4v, gif
Note: Select manually for higher accuracy, or leave blank to auto-detect.
Customize your input with more control.
Result
What would you like to do next?
Your request will cost $0.10 per minute of input video, with a 2x multiplier for resolutions above 1080p and a 2x multiplier for dynamic styling. Minimum charge: 1 minute.
Logs
VEED Subtitles API
VEED’s Subtitles API transforms raw footage into polished, publish-ready content with professional burned-in subtitles starting at a base rate of $0.10 per minute. Providing high-quality dynamic styling at scale, the system handles the entire "upload → transcribe → style → render" workflow, accepting video URLs and optional timing inputs. Built for automated video production pipelines where high-impact visual aesthetics and professional-grade rendering are required to engage audiences without manual editing.
Use Cases: Automated Video Production | Social Media Videos | Marketing Pipelines | Content Repurposing
Performance
VEED’s Subtitles API operates in a specialized high-fidelity niche, providing an end-to-end "video-in/video-out" solution where pricing is determined by output duration.
| Metric | Result | Context |
|---|---|---|
| Resolution Options | ≤ 1080p (1x) and > 1080p (2x) | Quality tiers balancing cost and visual fidelity. |
| Language Support | 125+ Languages | Comprehensive global reach with 98%+ auto-caption accuracy. |
| Preset Tiers | Basic (1x), Dynamic (2x) | Choose between standard styling or high-fidelity animations. |
| Cost per Minute | $0.10 – $0.40 | Base rate scales based on both resolution and preset complexity multipliers. The two multipliers compound - e.g. a 4K Dynamic render bills at $2.0 x 2.0 = 4x$ the base rate. |
| Input Requirements | Video URL + (Optional) SRT | Dual-input architecture allows for full transcription and custom timing. |
| Output Format | MP4 video | Standard web-compatible format with high-fidelity burned-in subtitles. |
High-Fidelity Rendering
The API utilizes a sophisticated backend pipeline that orchestrates transcription and styling before dispatching to a dedicated C++ render-node. This ensures that every animation, font shadow, and background highlight is rendered with consistency compared to VEED’s award-winning web editor.
What this means for you:
- Professional Presets at Scale: Gain instant access to high-impact presets without the time-consuming manual design work typically required in production.
- Global Accessibility: Instantly transcribe content in 125+ languages, enabling rapid global distribution.
- Platform-Ready: We automatically place subtitles in "safe zones" for every screen size, ensuring they aren’t hidden behind platform UI.
- Curated Brand Alignment: Maintain visual consistency by selecting from our curated library of fonts and colors designed to adapt to your brand's unique visual language.
- Flexible Timing Control: Use our high-accuracy auto-transcription or provide an SRT to ensure 100% precision for specialized terminology or timing.
- Single-API Simplicity: One endpoint manages the full chain—transcoding, transcription, styling, and rendering—saving days of integration time.
Specifications
| Spec | Details |
|---|---|
| Input Formats | Video: URL/presigned link; Optional: SRT |
| Output Formats | MP4 video |
| Resolution Tiers | ≤1080p (1.0x) and >1080 (2.0x) |
| License | Commercial use permitted via FAL Marketplace |
| Max Video Duration | ≤1080p → 2 hours; >1080p → 1 hour |
| Dynamic Presets | glass, whisper, glide, glide2, fusion, terminal, handwritten |
| Basic Preset | simple, plain, beans, corpo, boo, shadeplay, casper, capri, lowkey, vinta, diego, ali, slay, kitty, hustle, karl, sprout, flex, mint, rizz, vegas |
Style Meets Scale
- Most subtitle APIs stop at the transcript, leaving you to build the complex layers for timestamp alignment, line break logic, visual styling, and frame rendering. VEED handles the entire five-layer chain in a single API call, returning a post-ready MP4.
- Leverage VEED’s industry-leading transcription pipeline to instantly localize content for global audiences. Whether you are auto-transcribing or uploading an SRT, we support 125+ languages with high-fidelity styling.
- You aren't just getting generic text; you are getting the exact same subtitle presets powering millions of videos in the VEED app. Every preset is "battle-tested" and tuned for maximum readability on mute, with optimized font sizes, line spacing, and contrast levels.
- Our rendering engine automatically applies Safe Zones for every aspect ratio (9:16, 1:1, 16:9). This ensures your styled subtitles are never obscured by platform UI elements.
- Achieving high-quality, "scroll-stopping" subtitle presets at scale used to require manual editing or complex animation frameworks. We replace that labor-intensive process with a duration-based API that lets you ship a premium subtitle feature in days instead of weeks.
- By hosting on fal, you gain access to the broader VEED AI ecosystem. Chain your Subtitles styling with Fabric 1.0 for talking avatars or our Lip Sync API to build fully automated, high-end video content factories in a single environment.