CONTENT CREATION

Generate multilingual narrations for one article and log them in Airtable

From an Airtable record listing target languages, it produces an ElevenLabs voiceover per language plus a shared hero image, then writes each audio URL back to its language row.

CategoryContent Creation
Enginesim
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerAirtable record marked Ready for AudioAirtableAirtable
  • ActionRead source text and language rowsAirtableAirtable
  • ActionGenerate shared hero image from titleImage generation
  • ActionNarrate one MP3 per language with ElevenLabsElevenLabsElevenLabs
  • ActionUpload MP3s + image to DropboxDropboxDropbox
  • OutputWrite audio URLs and Done flag to each rowAirtableAirtable

What it does

Takes a single source article and a list of target languages from Airtable and produces one narrated MP3 per language using ElevenLabs multilingual voices, plus one shared hero image. Each finished audio file's location is logged back to its row in the tracker.

When to use it

Use it when you localize content for multiple markets and need audio versions in several languages from one English (or source) post, with a clean record of what was generated for whom.

How it works

  1. 1Marking an Airtable article record as Ready for Audio fires the trigger.
  2. 2The source text and the list of requested language rows are read.
  3. 3A hero image is generated once from the title to reuse across languages.
  4. 4For each language row, ElevenLabs narrates the text with the matching multilingual voice into its own MP3.
  5. 5Each MP3 and the shared image are uploaded to storage.
  6. 6The audio URL, voice id, and a Done flag are written back to each language row in Airtable.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AirtableBases, tables, views, automations.
  2. 2
    Connect Image generationManaged Nano Banana image renders, metered per image.
  3. 3
    Connect ElevenLabsText-to-speech, voice cloning.
  4. 4
    Connect DropboxFiles and folders.
  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.