Official recipe · Tool workflows
Prepare localized dubbed versions of approved media
Source-backed example. Practical decision guidance is proposed and untested; this is not a full implementation guide.
The problem
Reaching audiences in other languages requires coordinating dubbing jobs, translations and partial outputs without losing control of voice rights or cost.
Agent job
Resolve media files, target languages and workspace, submit dubbing jobs, manage documented pauses and eligible resumptions, and report each part's delivery status.
Expected output
Reviewable dubbed outputs, or disclosed server-only results where applicable, with incomplete work and additional approvals identified.
Where this framing comes from
- Core problem: Editorial purpose framing
- Agent job: Editorial purpose framing
- Expected output: Editorial purpose framing
- Relevant job roles: Editorial purpose framing
- Benefit type: Editorial purpose framing
Editorial framing and outcome limits
Describes the task’s purpose and intended output; measured benefit, safe unsupervised operation and successful delivery are not established by this framing.
Editorial synthesis based on the linked source. This framing does not add evidence of successful delivery or results.
Case-specific decision guidance · untested
Case-specific decision guidance and first checks are original proposals. The linked source supports the attributed task; this added guidance has not been executed.
Read the attributed source evidence and original caveats below ↓
Why use this
A creator localizing media may face different language variants, speaker-rights constraints and job parts that finish in different states. A completed processing status does not necessarily mean a usable file is available for delivery.
A per-language job plan could identify required choices, approvals and delivery checks before submission. It would make partial or server-only results visible and prevent retries or model changes from silently expanding the authorized spend.
Why an agent / simpler alternative
- Useful judgment
Reconcile media, locale and job-state requirements and distinguish recoverable partial work from decisions needing the owner.
- Simpler alternative
Use a single manual dubbing job for a short clip with one confirmed language and straightforward rights.
- Unsuitable when
Speaker consent, media rights, upload permission or spending authority is unresolved.
Proposed inputs
- Name
Approved media and rights brief
- Owner
Creator
- Minimum scope
Exact files, speaker-consent status and allowed localization uses
- Quality check
Verify permission covers uploading and proposed voice treatment.
- Name
Locale and job constraints
- Owner
Creator
- Minimum scope
Target language variants, workspace, budget boundary and delivery needs
- Quality check
Clarify ambiguous regional locales and acceptable output access.
Access and setup — proposed or unknown
- Proposed minimum
Offline media manifest and job-decision plan before any service upload.
- Compatibility unknowns
Unknown: exact runtime, service/model availability, regional locale support and downloadable-output eligibility.
- External actions requiring approval
Uploading media, starting paid work, splitting jobs, changing models or repeating processing; credit purchases remain owner-handled.
Expected deliverable and review checks
- Proposed artifact
Language/part manifest with proposed approvals, delivery states and unresolved quality checks.
- Critical checks
Every part maps to approved source media and locale.
Server-only completion is not represented as a delivered downloadable file.
- Missing output evidence
No dubbing job, preview, upload or delivery inspection is performed here.
Failure signals and proposed responses
- Signal
One part is complete while another failed or remains inaccessible.
- Why it matters
A single success label could hide an incomplete deliverable.
- Proposed response
Report each part separately and identify only authorized eligible resumptions.
- Signal
Recovery proposes a pricier model or another lip-sync pass.
- Why it matters
A retry may create an unapproved cost or creative change.
- Proposed response
Pause for the specific new choice and spending approval.
Effort and cost — unknown
- Setup work
Verify rights and define locales, parts and delivery requirements.
- Ongoing review
Inspect language quality, synchronization and actual file access.
- Unknowns
Unknown: credit use, turnaround, model quality and download restrictions.
First check — proposed, unexecuted
- Status
proposed_unexecuted
- Synthetic fixture
An invented job manifest has one downloadable part, one server-only result and a proposed paid retry.
- Acceptance checks
Delivery remains partial.
The retry stays blocked pending approval.
- Stop conditions
Real upload, voice-rights judgment or spending authority is required.
Limits
Editorial localization plan; source upload, consent, spending and locale limits remain referenced.
Editorial candidate. This is source-backed reporting or a documented workflow. BotCurrent has not independently tested this task. A proposed Canadian adaptation is not evidence of a Canadian deployment or compliance certification.
Original source
https://github.com/perso-ai/perso-dubbing-plugin/blob/main/skills/dubbing/SKILL.md ↗Attributed to: Perso AI
Official recipe- Original action type
- tool_action
- What the source supports
- Resolve input files, target languages and workspace; submit media for dubbing, handle split/model/credit pauses, monitor multi-part completion, resume eligible partial work and deliver each dubbed result or the disclosed server-only result.
- Source outcome limits
- Vendor recipe only. No dubbed delivery inspected. Initial upload, speaker consent and spending need explicit approval; free-plan outputs may remain server-only, and regional Canadian locale variants are not established.
- Evidence attribution caveat
- This official recipe describes a procedure; it does not prove successful execution or independently reproduced results.
- Source approval description
- Source asks for ambiguous locale/workspace choices, automatic splitting, free previews, pricier model changes and repeated lip-sync; credit purchases are handed to the user. It does not provide a complete initial upload, voice-rights and spending approval gate.
- Named tools
- Claude Code/Codex; Perso Dubbing API/plugin; optional lip-sync; ffmpeg merge; checkpoint files
- Model or version
- Unknown
- Publication date
- Unknown
- Source last checked
- 2026-10-14
- Demonstrated in Canada
- Unknown
- Canadian availability
- Unknown
- Proposed Canadian adaptation
- Proposed: offer reviewed English/French localization for Canadian creators, checking supported locales rather than treating ca as Canada; source lists no Canadian-English or Canadian-French regional variant.
- Recommended approval boundaries
- Approve the specific media upload, speaker consent and voice-use rights, languages and total cost before submission; review translation and voice representation; separately approve publishing or paid retries.