CONTENT CREATION

Auto-clip podcast episodes into vertical shorts

When a new episode audio lands in Dropbox, transcribe it, pick the most quotable 30-60 second moments, render captioned vertical clips, and drop them in a review folder.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew episode audio in Dropbox folderDropboxDropbox
  • ActionTranscribe audio with timestampsElevenLabsElevenLabs
  • ActionScore and select top clip momentsOpenAI
  • LogicDrop clips below length/confidence threshold
  • ActionRender captioned vertical videosReplicateReplicate
  • OutputStage clips in review folder + notify SlackSlack

What it does

Turns a finished podcast episode into a batch of ready-to-post vertical clips. It transcribes the audio, scores segments for hook strength, renders captioned short-form videos with a waveform, and stages them for human approval before anything goes public.

When to use it

Run this whenever you publish a new episode and want 3-5 social shorts without a video editor manually scrubbing for highlights. Best for shows that batch-produce clips weekly.

How it works

  1. 1A new audio file dropped in your `/episodes/incoming` Dropbox folder fires the trigger.
  2. 2ElevenLabs transcribes the audio to timestamped text.
  3. 3An LLM scores each segment for standalone clarity and hook strength, then selects the top moments.
  4. 4A filter discards any clip under 20 seconds or with a confidence score below threshold.
  5. 5Replicate renders each selected segment as a captioned vertical (9:16) audiogram video.
  6. 6The finished clips are written to a `/clips/review` Dropbox folder and a Slack message lists them for approval.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DropboxFiles and folders.
  2. 2
    Connect ElevenLabsText-to-speech, voice cloning.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect ReplicateImage, video, and model inference.
  5. 5
    Connect SlackChannels, DMs, threads, mentions.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    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.