You can't leak what you don't have.
You can't analyze call records you can't safely store. SecurePass redacts card numbers, health details and personal info from the audio itself, so you can keep every call as close to its original format as possible. Store it, analyze it, build test sets, and ship a better agent.
Your calls are your best data. Now you can keep them.
Redaction isn't the goal. The goal is everything you can do once a call is safe to store: find out why customers escalate, see how each release lands, and build test sets from real conversations.
Customer: Sure, my card number is silenced and I was charged twice for the March renewal.
The card number is gone. The context around it stays, so the analysis still has the full story.
- Sentiment across releasesUp from v2.3 to v2.4
- Top reason for escalationBilling dispute
- Failed intents this week38, down from 61
Whoever is on the line, keep the data.
Whether your calls are between people or with a voice agent, the problem is the same: the data you want sits next to the data you can't keep.
Human calls
You can’t analyze call records you can’t safely store.
SecurePass redacts card numbers, health details and personal info from the audio itself, so you can keep every call as close to its original format as possible. Store it, analyze it, build test sets, and ship a better agent.
Voice AI calls
You built the voice agent. Now prove it’s working.
Call recordings are the best evidence of how customers feel, but they’re full of card numbers, health info and personal details you can’t afford to leak. SecurePass redacts PCI, PHI and PII from your audio in real time, so you keep every insight, minus the risk.
Hear exactly what gets removed
A caller starts reading a card number, corrects a digit, then enters the remaining numbers using the keypad. Listen to the original and redacted versions of the same call. The sensitive information is removed while the rest of the conversation remains.
A billing call before and after SecurePass, with captions on the redacted spans. The video has sound.
Your data needs a home. In your pipeline or not.
You want the data, so it has to live somewhere. Send it to the pipeline you already run, or let SecurePass store the clean recording with its transcript and analysis attached.
In your pipeline
Plug SecurePass into what you already run. The redacted data goes wherever your data goes today.
- Post one recording to the REST API
- Point the callredact client at an S3 prefix, and results land back in your bucket
- Use the same steps as tools inside Autessa agents and scripts
Not in your pipeline
No storage or pipeline for call data yet? You don’t need one. Let SecurePass hold it.
- Stores the clean recording
- Keeps the transcript and analysis attached
- Ready for your dashboards, test sets and evaluations
curl -H "authorization: $KEY" \
-F file=@call.wav \
https://api.autessa.com/clients/call-redaction/redact- Redacted audio, same length and channels as the original
- Redacted transcript with each span marked
| Type | Start | End |
|---|---|---|
| CARD_NUMBER | 0:07.7 | 0:21.2 |
| CARD_CVV | 0:29.2 | 0:31.5 |
| CARD ENTRY (payer channel) | 0:03.2 | 0:36.5 |
Supported audio
- WAV
- mu-law
- MP3
- M4A
- Opus
Single or dual channel, with keypad tones. Recordings sent to the API are deleted after processing unless you choose otherwise, and redacted results are kept for 30 days.
Test the difficult cases before you integrate
Straightforward examples are not enough. Try interrupted numbers, corrections and keypad input to see how SecurePass performs on the recordings that matter to your product. Review the output and processing options before you build it into production.
Interrupted numbers
The caller reads the card in four groups while the agent says "uh huh" between them. SecurePass treats the groups as one card number and silences each piece, while the agent's replies stay in the recording.
Sample call: one CARD_NUMBER span from 0:14.6 to 0:30.4 across the agent's acknowledgments.
Corrections
A caller says "sorry, that last one was" and repeats a group. The corrected digits are part of the same card number, so they are redacted too, not left behind as a stray fragment.
Synthetic test call: the caller restates "that last group was one one one one" at 0:17.8, and the corrected digits are silenced.
Keypad tones
On an automated line the caller never speaks the number. SecurePass finds the touch tones themselves and silences them, while the prompts and the pound key stay.
Sample call: account number, card number, expiry, code and ZIP entered as tones, all silenced.
Not one sensitive value stored in full
Tested on 10M real calls: not one sensitive value stored in full, with 98% precision and only 2% over-redaction, in English and Spanish. You keep the conversation, not just the parts that were safe.
The best test is still your own audio. Send the calls your product actually handles and review the output yourself.
- English
- Spanish
- Zero full leaks
- 2% over-redaction
Autessa holds SOC 2 Type II, ISO 27001 and ISO 42001 certifications and supports HIPAA and GDPR compliance. Review its security documentation at trust.autessa.com.
- SOC 2 Type II
- ISO 27001
- ISO 42001
- HIPAA
- GDPR
- NIST 800-53 Moderate
- CJIS
- PCI DSS
- FedRAMP Moderate
Keep every call. Leak nothing.
Create an API key, send one call, and see what you can do with data that's finally safe to store.