Add narration, transitions, and captions to a slideshow
Creates a project from an uploaded PDF or PowerPoint file and generates an AI-narrated video walking through each slide. Upload the file via POST /v1/files/upload first.
Authentication
Request
Opaque file id of an uploaded PDF or PowerPoint file (e.g. vg_file_...). Upload the file first via POST /v1/files/upload.
Optional per-slide narration, in slide order, applied by index: each slide uses its matching entry, and an empty string makes that slide silent. If you provide fewer entries than slides, the remaining slides are silent; extra entries are ignored. Omit this field entirely to narrate each slide from its speaker notes in the uploaded file. To guarantee no narration on any slide, pass an empty array.
Aspect ratio as a width:height pair (e.g. 16 and 9 for 16:9). Not pixel dimensions.
Output language as a BCP-47 code (e.g. en, es, fr). Defaults to English.
Voice id from GET /v1/resources/tts-voices (e.g. vg_voic_...). A default voice is used when omitted. Any voice may be used here, including voices where supportsDirectToolExecution is false.
Optional avatar presenter id from GET /v1/resources/avatar-presenters (e.g. vg_pres_...). When set, the narration is delivered by a talking-head presenter avatar. Pass your voiceId to that endpoint to list presenters sorted by best match for the voice. Omit for a standard voiceover with no presenter.
Caption styling. Omit to use the default style with captions shown. Pass an object to override individual style fields (any omitted field uses the default). Pass null to hide captions entirely.
Optional file id of an uploaded logo image to overlay on the video (e.g. vg_file_...). Upload the image first via POST /v1/files/upload. Only image files are accepted.
Optional edits applied to the project after the video is built, in order. Each action runs asynchronously; the response returns one remix action id per action. Use this for background music, logo overlays, or caption changes beyond captionStyle.
Response
Opaque workflow run id (e.g. vg_work_...).
Opaque remix action ids (e.g. vg_rmix_...), one per remixActions entry in request order. Empty when no remix actions were requested. Each runs after the video is built; poll GET /v1/projects/{projectId}/remix-actions.