Skip to main content
Enterprise customers in healthcare, finance, and other regulated industries can now ensure that no customer text inputs or audio outputs are persistently stored in our systems after processing completes.

What products are configured for Zero Data Retention Mode?

ProductTypeEligible for Zero Data Retention?
Text-to-SpeechText InputYes
Text-to-SpeechAudio OutputYes
Voice CloningAudio SamplesNo

How Zero Data Retention works

When enabled, all customer text inputs sent to our text-to-speech engine are processed in memory to generate audio. Once complete, both the text and the generated audio are immediately redacted from our logging systems. This applies to all text sent for speech synthesis, including requests using cloned voices.

Supported models

TTS Zero Data Retention currently supports TTS-1.5-Mini and TTS-1.5-Max only. Legacy TTS-1 and TTS-1-Max models are not in the support scope.

Enterprise-level security

Workspace Configuration

Zero Data Retention is configured at the workspace level, allowing customers with strict data privacy requirements to maintain compliance.

Production Scale

Whether you’re handling protected health information or sensitive financial data, you get the security guarantees needed for production deployment at scale.

FAQs

TTS Zero Data Retention protects privacy by redacting all input texts from logs — including text sent to Cloned Voices — while only retaining the initial source audio required to build the voice itself. This is currently a workspace-level configuration managed by the Inworld Engineering team.
Yes. Zero Data Retention is configured per workspace. Contact our sales team to enable it for specific workspaces.
With Zero Data Retention enabled, original input text and audio output cannot be retrieved. Debugging and troubleshooting capabilities are limited to non-sensitive metadata only.
No. The TTS engine still receives the text to generate the audio. The redaction happens only at the logging layer, ensuring the record of what was said is not saved.