CONTENT CREATION
Route Low-Confidence Transcripts to Human Review Before Dubbing
After transcribing a new course video, checks the transcription confidence score and routes weak transcripts to a Linear review ticket while letting clean ones proceed straight…
How it runs
The automated pipeline, trigger to output.
- TriggerNew video uploaded to DropboxDropbox
- ActionTranscribe with Hugging Face Whisper and score confidenceHugging Face
- LogicBranch on average confidence vs threshold
- ActionOpen Linear review ticket for low-confidence segmentsLinear
- ActionGenerate dub with ElevenLabs for clean transcriptsElevenLabs
- OutputStore transcript and dub to R2Cloudflare R2
What it does
This adds a quality gate between transcription and dubbing. Every freshly transcribed lesson is scored for confidence; high-confidence transcripts flow straight into dub generation, while low-confidence ones are held and turned into a Linear ticket for a human to correct before any audio is produced.
When to use it
Use it when source audio quality varies and a bad transcript would poison every downstream translation and dub. It prevents wasting voice-synthesis spend on garbage input and keeps errors from compounding across languages.
How it works
- 1A new video upload to Dropbox fires the trigger.
- 2Hugging Face Whisper transcribes the audio and returns per-segment confidence scores.
- 3Branch on the average confidence against your threshold.
- 4If below threshold, create a Linear issue with the shaky segments attached for manual correction, then stop.
- 5If above threshold, generate the dubbed track with ElevenLabs.
- 6Store the approved transcript and dub to R2 for downstream translation steps.
Set it up
What you configure once, before turning it on.
- 1Connect DropboxFiles and folders.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Connect ElevenLabsText-to-speech, voice cloning.
- 5Connect Cloudflare R2Object storage, S3-compatible.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Content Creation workflows
Build a Dropbox B-roll library from exported blog drafts
Triggers when a new blog draft file lands in a Dropbox folder, generates a Replicate B-roll clip for each paragraph.
Generate B-roll clips when a blog post is marked Ready in Notion
Watches a Notion blog database for posts flipped to 'Ready', splits the body into paragraphs, and generates a short B-roll video clip for each paragraph with Replicate.
On-demand: turn a blog URL into narrated B-roll clips
Accepts a blog URL via webhook, scrapes the article, generates a B-roll clip per paragraph with Replicate and a voiceover with ElevenLabs.
On-Demand Screenshot Freshness Report from a Slack Command
A writer requests a freshness check in Slack for a specific docs page; the workflow inspects every screenshot on that page, scores each by age and version gap.
Sync a Figma master frame into localized hero renders
Pulls the current master hero frame and its text layers from Figma, generates a localized image variant for each locale defined in Airtable.
Research-driven localized hero banners tuned per market
An agent researches cultural and seasonal cues for each target market, adapts the master hero concept to fit local context, generates a tailored image per locale.
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.