Skip to main content
To generate audio or video, submit a content item via Create and generate content. That endpoint queues TTS and media processing — it is the main entry point for integrations. Most workflows follow three steps:
  1. Create — POST article HTML, manual segments, or an audio upload. See Processing types.
  2. Wait for completion — Use webhooks to be notified when status is processed (or handle error / skipped). See the Webhooks guide.
  3. Retrieve — Call Get content with ?segments=full when you need segment data for the player.

Create and generate content

Submit content and start audio or video generation.

Processing types

Choose auto_segment, manual_segment, or audio_upload.

Content object

Properties returned on every content item.

Regenerate content

Re-run generation after updating an existing item.

​
Endpoints

GoalEndpoint
Generate audio or video for new contentCreate and generate content
Fetch a content itemGet content
Update a content itemUpdate content
Delete a content itemDelete content
Re-generate after editsRegenerate content
Generate a summarySummarize content
Upload audio for audio_uploadUpload file
List content itemsList content
The other API reference sections — Extraction, Pronunciation settings, Script settings, Video settings, and Background music settings — configure project defaults. They do not generate content on their own. Use the Items endpoints below the developer guide for that.

​
Identifiers

FieldUse
idBeyondWords UUID. Use with player and analytics endpoints.
source_idYour CMS or feed identifier. Use for upserts and syndication.
source_urlPublic article URL. Use with player by source URL.

​
Processing status

StatusMeaning
draftCreated but not queued for generation.
queuedWaiting to be processed.
processingAudio or video is being generated.
processedGeneration complete. Audio and segment data are available.
skippedGeneration was skipped (for example, insufficient credits).
errorGeneration failed. Update the item or call Regenerate content.