CONTENT CREATION

Auto-Subtitle and Dub New Course Videos on Dropbox Upload

Watches a Dropbox course-videos folder, transcribes each new lesson, generates translated subtitle tracks plus AI voice dubs in your target languages.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew video added to Dropbox course-videos folderDropboxDropbox
  • ActionTranscribe audio with Hugging Face WhisperHugging FaceHugging Face
  • LogicSkip non-video files; continue for mp4/mov
  • ActionTranslate and time subtitles per target languageHugging FaceHugging Face
  • ActionGenerate dubbed voice tracks with ElevenLabsElevenLabsElevenLabs
  • OutputStore subtitles and dubs to R2 by lessonCloudflareCloudflare R2

What it does

When an instructor drops a new lesson video into a shared Dropbox folder, this pipeline produces a complete localized package: a source-language transcript, translated `.srt` subtitle files, and dubbed audio tracks in each target language, all archived to R2 under a stable per-lesson key.

When to use it

Use it when you publish course content regularly and want localization to happen the moment a video lands, instead of batching it manually. Best for teams with a fixed set of target languages defined once.

How it works

  1. 1A new file in the Dropbox `/course-videos` folder fires the trigger.
  2. 2The video audio is sent to Hugging Face Whisper for source-language transcription with word timings.
  3. 3Branch on file type: skip non-video files, continue for `.mp4`/`.mov`.
  4. 4For each configured target language, the transcript is translated and timed into an `.srt` subtitle file.
  5. 5ElevenLabs generates a dubbed voice track per language from the translated text.
  6. 6All subtitle files and audio dubs are written to R2 under `lessons/{lessonId}/{lang}/`.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DropboxFiles and folders.
  2. 2
    Connect Hugging FaceModels, datasets, spaces — the open-source hub.
  3. 3
    Connect ElevenLabsText-to-speech, voice cloning.
  4. 4
    Connect Cloudflare R2Object storage, S3-compatible.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.