sync. labs

Display the Sync image/audio uploader in ChatGPT. The widget can stage a selected local image or audio file as a Sync asset and start a lipsync generation. It does not accept video files.

open-upload-widget

Create a project to group related generations and assets. Pass the returned `id` as `projectId` on generate_create-generation or assets_create so they show up together in Studio.

projects_create

Get a project by id.

projects_get

Search and paginate your accessible Sync projects. Use the returned id as projectId in create-lipsync to work in the same project as the Sync web app.

projects_get-all

Read generation history for an accessible Sync project. Requires a projectId returned by projects_get-all. Pass limit and the last returned generation id as cursor to load another page. These are the same records used by the Sync web app.

projects_get-generations

Use this when the user wants to translate and dub a video into another language with matching lip movements. Not for subtitles only or translating a text document. Requires a saved video asset, selected project, model, and persistent idempotency key. This is a paid action: confirm the requested language, configuration and estimated cost with the user before calling. Use generate_estimate-cost with workflow=translate-and-dub when that input is supported, and disclose any excluded external provider charges. Without the combined breakdown, lip-sync pricing is not the full workflow cost. The API manages dubbing and final rendering under the returned generation id. Poll generate_get-generation for that same id until COMPLETED; do not create another job to finish or recover it.

create-translate-and-dub

Read the source and target languages supported by the current translation API. Does not create a generation or estimate pricing.

get-translation-options

Stage an image, video, or audio file in Sync asset storage and return a durable assetId. The file must be a host-provided object with a temporary HTTP download URL. Public URL strings are not accepted. This creates a media asset but does not start a lipsync generation.

upload-media

Use this when the user explicitly wants to save a reusable clone of their own voice or a voice they have permission to clone. Confirm the sample and name first; plan limits and provider requirements apply, so do not claim this is free. Pass exactly one Sync-hosted `url` or accessible `assetId`, plus `provider` (elevenlabs) and `name`. Upload/register local samples first. Video samples have audio extracted by the API. Returns a Sync `id`: use that id as `voiceId` in create-lipsync with script, not the provider-specific `voiceId` field. Do not use for Edit Dialogue previews, selecting an existing voice, or designing a voice from a text description. This creates a persistent voice and is not idempotent. On timeout or uncertain failure, list voices and reconcile; never automatically retry. Surface API plan limits, sample errors and duplicate-name errors without retrying or changing accounts.

voices_clone-voice

List available voices: premade ElevenLabs voices plus voices your org has cloned. For "make this image/video say X", use an available returned voice `id` as `voiceId` in create-lipsync with `script` directly. Respect any returned restriction. Use this to find an existing clone before creating another.

voices_get-voices

Preview timed word changes/removals in the original speaker’s voice. This is a synthesis action. Use a completed transcription, or a prior preview of this source when reopening. Confirm edits first. Never retry an ambiguous creation automatically. This is not arbitrary full-transcript replacement.

Use this to start correcting or removing spoken words in a saved single-speaker video while keeping the original speaker voice. Transcribes timed words for Edit Dialogue; not whole-script replacement, translation, or choosing a different voice. Transcription is unbilled and identical sources reuse their existing job. Does not replace dialogue or generate a video.

Generate the final video from an approved completed audio preview matching the current edits. Confirm the estimate first. Reuse the same idempotency key and inputs for recovery; poll generate_get-generation for the returned ID.

Estimate final video cost using the completed dialogue preview and canonical server retiming. Does not generate or reserve credits.

Check whether the connected API supports timed-word Edit Dialogue. Does not transcribe, synthesize or generate.

Read one existing Edit Dialogue audio preview. Partial completion must be disclosed, not described as every edit succeeding.

Read the same transcription job until complete. Requires its original saved video and accessible project.