Content credentials
The high-quality models in the Azure text to speech avatar feature generate realistic avatar videos from text input. To improve the transparency of the generated content, the Azure text to speech avatar provides content credentials, a tamper-evident way to disclose the origin and history of the content. Content credentials are based on an open technical specification from the Coalition for Content Provenance and Authenticity (C2PA), a Joint Development Foundation project.
What are content credentials?
Content credentials in the Azure text to speech avatar provide customers with information about the origin of an avatar video. This information is represented by a manifest attached to the video. The manifest is cryptographically signed by a certificate that traces back to Azure text to speech avatar.
The manifest contains several key pieces of information:
| Field name | Field content |
|---|---|
"generator" |
This field has a value of "Microsoft Azure Text To Speech Avatar Service" for all applicable videos, attesting to the AI-generated nature of the video. |
"when" |
The timestamp of when the content credentials were created. |
Content credentials in the Azure text to speech avatar can help people understand when video content is generated by the Azure text to speech avatar system. For more information on how to responsibly build solutions with text to speech avatar models, visit the Text to speech transparency note.
Limitations
The content credentials are only supported in video files generated by batch synthesis of text to speech avatar, and only mp4 file format is supported.
How do I use content credentials in my solution today?
You can use content credentials by ensuring that your Azure text to speech avatar generated video files contain content credentials.
No extra set-up is necessary. Content credentials are automatically applied to all applicable videos generated by the Azure text to speech avatar.
Verifying that a video file has content credentials
As for now, self-serve verification of content credentials for text to speech avatar video isn't yet available. You can contact Microsoft for verification of content credentials of Azure text to speech avatar generated videos.