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

What data is covered by Zero Data Retention?

DataTypeEligible for Zero Data Retention?
Audio InputCustomer-submitted audio (file or stream)Yes
Transcription OutputTranscribed text returned by the APIYes
Usage MetadataRequest duration, model ID, timestampsNo — retained for billing

How Zero Data Retention works

When a request is processed, customer audio is sent to the selected provider and transcribed in memory. Once complete, both the original audio and the transcription output are immediately redacted from our logging systems. This applies to all requests — sync (file upload) and WebSocket (streaming) — across every supported provider.

Supported models

Zero Data Retention applies to all STT models available through the Inworld STT API. Each upstream provider maintains its own ZDR guarantees:
ProviderModelsDetails
Inworldinworld/inworld-stt-1Processed in memory; redacted from logs after completion
AssemblyAIassemblyai/*ZDR enabled for streaming (AssemblyAI docs)
Groqgroq/whisper-large-v3No customer inputs or outputs retained by default (Groq docs)

Enterprise-level security

Inworld’s platform is SOC 2 Type II certified and HIPAA and GDPR compliant. For full details on our security posture, certifications, and data handling practices, see our Security page.

Workspace Configuration

Zero Data Retention is enforced across all STT providers routed through the Inworld API, giving you a single privacy guarantee regardless of which model you use.

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

STT Zero Data Retention protects privacy by redacting all customer audio and transcription outputs from logs immediately after processing. Only non-sensitive usage metadata (request duration, model ID, timestamps) is retained for billing and service monitoring.
Yes. All models available through the Inworld STT API — Inworld, AssemblyAI, and Groq — operate under Zero Data Retention.
No. Audio processed through the Inworld STT API is never used for training by Inworld or any upstream provider.
With Zero Data Retention enabled, original audio and transcription text cannot be retrieved. Debugging and troubleshooting capabilities are limited to non-sensitive metadata only.
No. The STT engine still receives the audio to generate the transcript. The redaction happens only at the logging layer, ensuring no record of the audio or transcript is saved.