Captions & On-Screen Text · Versely AI

    Add Subtitles to a Video Automatically — No Manual Timing

    You upload the video. The words appear, timed to the voice.

    Manually typing and timing subtitles is the part of editing nobody enjoys — line by line, scrubbing back and forth to match timestamps to speech. Versely's captioning tool does the transcription and the timing in one pass.

    This is the same underlying engine as add-captions-to-video, but the intent here is accessibility and comprehension — getting an accurate, readable subtitle track on screen — rather than a specific visual hook style. Pick a plain, legible preset if that's your goal, or a premium one if you want it to double as a stylistic hook.

    Powered by

    add_veed_captionspreview_caption_stylelist_caption_fonts

    Add styled, auto-transcribed captions to a video using the VEED Subtitles model (fal.ai veed/subtitles). Burns aesthetic preset styles (Glass, Whisper, Fusion, Glide, etc.) — different from add_dynamic_captions, which is the word-level animated style. Use when the user wants polished social-ready captions with a chosen visual look, or asks for VEED captions specifically. Also offer this proactively as a finishing step after any video / movie / workflow run that produces video content. Two preset tiers: BASIC (1× credit cost, 21 presets — simple/plain/beans/corpo/etc.) and DYNAMIC (2× credit cost, 9 premium presets — glass/whisper/glide2/fusion/glide/terminal/handwritten/backdrop/backdrop2). Default to preset 'glass' for a modern look unless the user specifies a vibe. Supports 165 language codes for transcription (en-US, en-GB, es-ES, es-MX, fr-FR, de-DE, it-IT, pt-BR, ja-JP, ko-KR, zh, ar-SA, ru-RU, etc.).

    What to tell the agent

    Versely's agent maps this plain-English request directly onto add_veed_captions. You don't need to know the parameter names — just describe what you want.

    Transcribe and add subtitles to this video automatically — use a plain, easy-to-read style, language en-US.

    How it works

    1. 1. Upload your video

      Any clip with a clear spoken audio track works — interviews, explainers, lectures, vlogs.

    2. 2. Set the source language

      Tell the agent which language is spoken (165 codes supported) so the transcription engine listens for the right phonemes.

    3. 3. Pick a readable preset

      For accessibility-first subtitles, a BASIC preset like 'simple' or 'plain' keeps the focus on legibility over style.

    4. 4. Render and review

      Versely returns the video with subtitles burned in, timed line-by-line to the speech. Spot-check names, numbers and jargon — ASR isn't perfect on those.

    What it costs

    BASIC presets (the plain, accessibility-style looks) bill at the standard 1× rate; DYNAMIC presets cost 2×. Run estimate_cost in chat before a long render to see the exact credit price.

    The formula behind that number: What do captions cost across a month of clips? multiplies one base render by a style tier, so an aesthetic choice doubles the bill.

    Limits & things to know

    • Subtitles are burned into the video pixels, not a separate toggleable .srt/.vtt track — decide on wording and language before the final render.
    • Transcription quality drops with heavy accents, cross-talk, or noisy audio.
    • This transcribes the spoken language as-is; it does not translate to another language mid-process.
    • 165 language codes are supported, but coverage and accuracy vary by language.

    Who uses this

    • Accessibility compliance for course and training video
    • Silent-autoplay social feeds
    • Interview and podcast clips
    • International audiences watching in their non-native language

    Frequently asked questions

    Do I need to type the subtitle text myself?+

    No. add_veed_captions transcribes the video's spoken audio automatically and times each caption line to the speech.

    Can I get a plain, non-flashy subtitle look?+

    Yes — the BASIC preset tier includes plain, simple, and other minimal styles built for readability rather than visual flair, at the standard credit rate.

    How many languages can it transcribe?+

    165 language codes, covering major world languages and many regional variants (e.g. es-ES vs es-MX, en-US vs en-GB).

    Will it catch every word correctly?+

    It's automatic speech recognition, so accuracy depends on audio clarity — proper nouns, brand names, and heavy background noise are the most common places it needs a manual fix afterward.

    Related Versely tools

    Related editing jobs

    Add Subtitles Automatically inside Versely

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.