SUMMARIZATION
Turn a long Dropbox manuscript into chapter-marked ElevenLabs narration
Watches a Dropbox folder for new long-form documents, detects chapter boundaries, narrates each chapter with ElevenLabs.
How it runs
The automated pipeline, trigger to output.
- TriggerNew manuscript added to Dropbox watch folderDropbox
- ActionOpenAI extracts chapter outline with titles and offsetsOpenAI
- LogicValidate chapter lengths; merge sub-minimum stubs
- ActionElevenLabs narrates each chapter with one voiceElevenLabs
- ActionBuild JSON TTS index (chapter, file, duration, offset)
- OutputWrite chapter audio + index to Dropbox delivery folderDropbox
What it does
Converts a long manuscript dropped into Dropbox into a fully chaptered audiobook. It splits the document at chapter boundaries, generates narration for each chapter as its own audio file, and produces a machine-readable index mapping chapter titles to file names and start offsets.
When to use it
Use it when you publish long-form content (books, reports, course manuals) and need consistent, repeatable narration without manually slicing files or re-recording. Ideal for self-publishers and content teams who want a hands-off pipeline from final draft to listenable chapters.
How it works
- 1A new document landing in the watched Dropbox folder fires the trigger.
- 2OpenAI parses the text and returns a structured chapter outline with titles and character offsets.
- 3A loop step checks each detected chapter is above a minimum length, merging stub sections so you never get a 4-second track.
- 4ElevenLabs synthesizes narration for each chapter with a single, consistent voice.
- 5The flow assembles a JSON TTS index (chapter, file, duration, offset) and uploads it.
- 6The chapter audio files and the index are written back to a delivery subfolder in Dropbox.
Set it up
What you configure once, before turning it on.
- 1Connect DropboxFiles and folders.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect ElevenLabsText-to-speech, voice cloning.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Summarization workflows
On-submit Loom standup roll-up archived to Confluence
When a standup video is submitted via webhook, transcribes it, generates a per-person written summary, and appends it to a running team standup page in Confluence.
Front Escalation Handoff Doc in Notion
When a Front escalation closes, drafts a structured handoff document in Notion capturing the resolution, customer commitments, and open follow-ups, then alerts the AE in Slack.
Front Escalation War-Room Brief to Slack
On a Front escalation, posts a concise threat-assessment brief to a Slack channel only when the AI judges the situation high-severity.
VIP Front Escalation Instant Exec Page-Out
Detects escalations from VIP accounts in Front, generates a one-paragraph executive recap, and pages the named account exec via Slack and Salesforce task within minutes.
Release health note per Vercel deploy
When a Vercel deploy goes live, summarizes the Sentry errors observed in the release window into a plain-English health note that separates brand-new error classes…
Rollback recommendation when a deploy spikes errors
When a Sentry alert fires for an error spike, attributes it to the most recent deploy, summarizes whether the spike is dominated by new error classes introduced by that release.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.