Voice

View as Markdown

Voice capabilities may support speech-to-text, text-to-speech, or related conversation experiences. Before enabling them, confirm audio processing, retention, and egress policies.

Capability Boundary

AreaGuidance
Data HandlingDefine whether audio is uploaded externally, stored, and retained.
Model ServiceUse approved voice models or services.
User AuthorizationShow clear notices for audio that may include personal or meeting information.
AuditRecord call status, errors, and associated requests.

Before Configuration

  • Confirm voice-service credentials, models, and language support.
  • Define the users, groups, and scenarios allowed to use voice.
  • Check privacy, compliance, and meeting-recording requirements.

Verification

  • Test recognition or synthesis with low-risk audio.
  • Confirm unauthorized users cannot use the capability.
  • Check user-facing messages for failures, timeouts, or unsupported languages.