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.

veed/subtitles

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.

Inference

Commercial use

Partner

Schema

LLMs

Playground API Examples

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

veed/subtitles

Schema

LLMs

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Video Url*

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

Preset*

Language

Note: Select manually for higher accuracy, or leave blank to auto-detect.

Additional Settings

Customize your input with more control.

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. Setting a translation_language adds a flat +$0.20 / minute surcharge on top. Minimum charge: 1 minute.

Result

Idle

What would you like to do next?

Download

{
  "video": {
    "url": "https://v3b.fal.media/files/b/0a9a3949/c5_GsxsCQaMZ3z-g2ehs2_substyle-example-output-compilation-v3.mp4",
    "file_name": null,
    "file_size": null,
    "content_type": null
  }
}

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 → optionally translate → style → render" workflow, accepting video URLs and optional inputs (SRT, custom dictionary, translation target language). 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 | Caption Localization

For detailed integration guide, check this page.

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	200+ Languages (150+ for transcription, 200+ for translation)	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 – $0.60	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, custom vocabulary, translation target	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 150+ source languages and translate into 200+ targets, 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. -Localise on the Fly: Set a translation_language to render subtitles in a different language from the source audio — the pipeline transcribes, translates, then styles in one call. Covers 200+ BCP-47 target codes (broader than transcription, includes languages without STT models like ab, ace, ak).
Brand-Aware Transcription: Pass a custom vocabulary list of brand names, product names, and jargon to override common ASR mishearings ("VEED" → "vid"). Whole-word and case-insensitive matching, up to 100 entries.
Text-Behind Subtitles: The backdrop / backdrop2 presets render subtitles behind people and objects in the frame, so the subject occludes the text as they move — for cinematic, scroll-stopping depth.

Specifications

Spec	Details
Input Formats	Video: URL/presigned link; Optional: SRT (raw or URL)
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, backdrop, backdrop2
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 150+ source languages with high-fidelity styling, and can translate into 200+ target languages.
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.

VEED Subtitles API

Use Cases: Automated Video Production | Social Media Videos | Marketing Pipelines | Content Repurposing | Caption Localization

For detailed integration guide, check this page.

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	200+ Languages (150+ for transcription, 200+ for translation)	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 – $0.60	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, custom vocabulary, translation target	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

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 150+ source languages and translate into 200+ targets, 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. -Localise on the Fly: Set a translation_language to render subtitles in a different language from the source audio — the pipeline transcribes, translates, then styles in one call. Covers 200+ BCP-47 target codes (broader than transcription, includes languages without STT models like ab, ace, ak).
Brand-Aware Transcription: Pass a custom vocabulary list of brand names, product names, and jargon to override common ASR mishearings ("VEED" → "vid"). Whole-word and case-insensitive matching, up to 100 entries.
Text-Behind Subtitles: The backdrop / backdrop2 presets render subtitles behind people and objects in the frame, so the subject occludes the text as they move — for cinematic, scroll-stopping depth.

Specifications

Spec	Details
Input Formats	Video: URL/presigned link; Optional: SRT (raw or URL)
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, backdrop, backdrop2
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 150+ source languages with high-fidelity styling, and can translate into 200+ target languages.
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.

veed/subtitles, details and endpoints

veed/subtitles

Input

Result

What would you like to do next?

veed/subtitles, details and endpoints

veed/subtitles

Input

Result

What would you like to do next?

veed/subtitles, details and endpoints

veed/subtitles

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

Input

Result

What would you like to do next?

VEED Subtitles API

Performance

High-Fidelity Rendering

Specifications

Style Meets Scale

VEED Subtitles API

Performance

High-Fidelity Rendering

Specifications

Style Meets Scale