CONTENT CREATION

Produce dubbed multilingual audiograms from one episode

Takes a flagged episode, dubs key segments into target languages with voice cloning, renders captioned audiograms for each language, and stores them in cloud storage by locale.

CategoryContent Creation
Enginesim
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerEpisode tagged 'localize' in AirtableAirtableAirtable
  • ActionTranscribe source audio with timestampsElevenLabsElevenLabs
  • ActionSelect and translate key segmentsOpenAI
  • ActionDub segments with cloned voiceElevenLabsElevenLabs
  • ActionRender captioned audiograms per languageReplicateReplicate
  • OutputUpload to S3 by locale + log links to AirtableAWS S3

What it does

Expands one episode into localized audio assets for international audiences. It transcribes and translates standout segments, dubs them using the host's cloned voice per language, renders captioned audiograms for each locale, and files everything in cloud storage organized by language.

When to use it

Use it when your show has a meaningful audience outside its primary language and you want native-language clips without re-recording. Best for shows with evergreen, segment-friendly content.

How it works

  1. 1Tagging an episode 'localize' in Airtable triggers the run, with target languages listed in the row.
  2. 2ElevenLabs transcribes the source audio with timestamps.
  3. 3An LLM selects 2-3 strong standalone segments and translates each into the target languages.
  4. 4ElevenLabs dubs each translated segment using the host's cloned voice.
  5. 5Replicate renders a captioned audiogram per segment per language.
  6. 6Finished files are uploaded to an S3 bucket under per-locale prefixes, and the Airtable row is updated with the links.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AirtableBases, tables, views, automations.
  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 AWS S3Buckets, objects, signed URLs.
  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.