Hire an AI multilingual voiceover and subtitle producer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A spoken voiceover file from your script
• A dubbed version in each language, with a transcript you can correct
• Subtitles for each corrected version, with timing

How it does the job well

• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.
• Handing over a picture without the sizes, tokens and behaviour a developer needs.

What a good result looks like

An example, not your task: You have a script for a video, lesson or ad and need more than one language.

• Step 1: Voiceover. The spoken file, the text used, the voice and style, and the clarity, pace and pronunciation checks.
• Step 2: Dubbed versions. One audio file per language, a transcript per language and a list of lines to refine.
• Pause for native speakers. Each speaker marks wrong words, names or tone, and you regenerate the flagged lines.
• Step 3: Subtitles. A subtitle file with timing for each corrected language, made from the final audio.
• Hand-back summary. Each step's file and every MISSING line in one list.

How the work is checked

• The spoken text in step 1 matches your script word for word.
• Every dubbed language has a native speaker's sign-off, or it is left out and the summary says so.
• Names and product terms are right in each language.
• The subtitles match the corrected audio, not the first dub.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Make the voiceover. Takes your exact text, voice and style, generates the spoken file, and checks clarity, pace and pronunciation before it saves the final.
• Dub into other languages. Creates a dubbing project from the voiceover, checks the source transcript and adds one language at a time, keeping the voice.
• Pause for native speakers. A native speaker for each language listens, marks wrong words, names or tone, and you regenerate the lines they flag.
• Write the subtitles. Transcribes each corrected file with word timing and exports subtitles for every language.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id make-a-voiceover-and-ship-it-in-other-languages only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/make-a-voiceover-and-ship-it-in-other-languages/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your script, exactly as it should be spoken
• The voice and delivery style you want
• The languages you need
• A native speaker for each language to check the result
• An OpenAI key for the voiceover and an ElevenLabs key for dubbing and subtitles

Functions and deliverables

• Multilingual voiceover and subtitle producer: Share a script, target languages and approved voice. Get audio, dubbed versions and subtitles where the needed production tools are available.
  • A spoken voiceover file from your script
  • A dubbed version in each language, with a transcript you can correct
  • Subtitles for each corrected version, with timing
• Voiceover maker: Give it exact text, voice and delivery style. With Python and an OpenAI API key, get one audio clip or a batch.
  • One or more audio files, saved in output/speech/
  • A short list of the text, voice and settings used
  • A re-run with one change if you ask for it
  Source: OpenAI.
• Video dubbing editor: Share a video or podcast. Get versions in other languages that keep each speaker's voice, ready to correct.
  • An editable source transcript
  • A dubbed track per language in the original voices
  • Segment-level translation edits
  • Regenerated audio after each change
  Source: ElevenLabs.
• Subtitle and transcript maker: Turn a meeting, interview or video into a written transcript with who said what and the time of each word. Uses ElevenLabs speech to text and your own API key.
  • A full text transcript
  • Speaker labels
  • Word-level timestamps
  • Word timing you can turn into a subtitle file
  • A request ID to track usage
  Source: ElevenLabs.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one

Tasks you can use it for

• You have a script for a video, lesson or ad and need more than one language.
• You want one voice across languages.
• You need subtitles that match the final audio exactly.

Limits to check before starting

• You only have notes, not a final script: write the script first (the Read-aloud speech editor helps with a speech), then come back.
• You only want captions on a finished video: use the Video caption maker in your brand font.
• You have no native speaker for a language: skip that language, since this needs a person to check each dub before subtitles.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the final script. Change it now, not after dubbing.
• Stop after step 2 and send each language to a native speaker.
• Give back their fixes, then run step 3 for the subtitles.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/make-a-voiceover-and-ship-it-in-other-languages for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.