You can generate a pre-recorded video of your agent's avatar speaking text you provide — a video greeting, a training clip, an onboarding walkthrough, or an announcement. The API renders a lip-synced, voiced video you can preview, download, and reuse anywhere.
Create a recording
For code samples and implementation details, see the Napster API developer documentation.
Recordings are generated asynchronously. The response returns a recording ID and a status of pending.
Check status and download
For code samples and implementation details, see the Napster API developer documentation.
The download URL is time-limited — retrieve it when you are ready to download. Poll the recording status until it reads completed before requesting the URL.
Manage recordings
- GET /public/companions/{companionId}/recordings — list all recordings for a companion.
- GET /public/companions/{companionId}/recordings/{recordingId… — get status and details.
- GET /public/companions/{companionId}/recordings/{recordingId… — get a time-limited download URL once completed.
- DELETE /public/companions/{companionId}/recordings/{recordin… — remove a recording.
Common use cases
- Video greetings for landing pages or email campaigns.
- Onboarding walkthrough videos embedded in your product.
- Training clips and announcements reused across multiple channels.
- Pre-produced content for events or kiosk displays.
Note: Generation can take several minutes depending on the length of the text. Plan ahead and generate recordings before they are needed, not at the moment of use.