What leaves your device, and exactly when
Most transcription tools have to take your audio to work. Cohearo's architecture means it never needs to. This page is the specific version of that claim — what is processed where, what we store, for how long, and what we don't yet certify.
Your audio
Recording, transcription and speaker separation all run on your processor. There is no code path that uploads an audio file — not for processing, not for quality, not for support.
- Captured, transcribed and diarized locally
- Held on your disk for 72 hours so you can export it
- Removed automatically after that window
- Works with the network off
Transcript text, for AI
Turning a raw transcript into minutes or a user story runs on our servers. That step sends the transcript text — never the audio — and only for the recording you pressed the button on.
- Sent only on an explicit enhancement request
- Text only: no audio, no voice data
- Processed and returned, not used to train models
- Skip it entirely and the app still does its main job
Transcripts you sync
Whether a transcript reaches our servers depends on the mode you pick at sign-in. Cloud mode syncs new transcripts automatically; On-device mode keeps them private unless you push one yourself.
- Chosen once at sign-in: On-device or Cloud
- On-device recordings stay private by default
- You can still push a single recording to the cloud yourself
- Only synced transcripts are reachable by an assistant over MCP
Every kind of data, and where it sits
If your security reviewer wants one table, this is it.
Meeting audio
- Where it lives
- Your disk only
- Retention
- 72 hours, then removed
- Who can reach it
- You. It is never transmitted.
Transcript (local)
- Where it lives
- Your disk
- Retention
- Until you delete it
- Who can reach it
- You
Transcript (synced)
- Where it lives
- Our storage, encrypted at rest
- Retention
- Free plan: up to 7 days · Paid plan: until you delete it or close your account
- Who can reach it
- You, and assistants you connect over MCP
Text sent for AI enhancement
- Where it lives
- Our servers, in transit
- Retention
- Processed and returned; not retained for training
- Who can reach it
- The model provider processing the request
Speaker labels
- Where it lives
- With the transcript
- Retention
- Same as the transcript
- Who can reach it
- Same as the transcript
Speaker voice profile
- Where it lives
- Your disk; the voice embedding never leaves it
- Retention
- Until you delete the profile
- Who can reach it
- You. The voice embedding is never transmitted; in Cloud mode, the profile's identifier and name may sync so the same person is recognized across devices.
Account and billing
- Where it lives
- Our systems and our payment processor
- Retention
- While the account exists, plus statutory records
- Who can reach it
- You and our support team
Product analytics
- Where it lives
- Our systems
- Retention
- Aggregate usage counts
- Who can reach it
- Us. No transcript content is included.
| Data | Where it lives | Retention | Who can reach it |
|---|---|---|---|
| Meeting audio | Your disk only | 72 hours, then removed | You. It is never transmitted. |
| Transcript (local) | Your disk | Until you delete it | You |
| Transcript (synced) | Our storage, encrypted at rest | Free plan: up to 7 days · Paid plan: until you delete it or close your account | You, and assistants you connect over MCP |
| Text sent for AI enhancement | Our servers, in transit | Processed and returned; not retained for training | The model provider processing the request |
| Speaker labels | With the transcript | Same as the transcript | Same as the transcript |
| Speaker voice profile | Your disk; the voice embedding never leaves it | Until you delete the profile | You. The voice embedding is never transmitted; in Cloud mode, the profile's identifier and name may sync so the same person is recognized across devices. |
| Account and billing | Our systems and our payment processor | While the account exists, plus statutory records | You and our support team |
| Product analytics | Our systems | Aggregate usage counts | Us. No transcript content is included. |
What you can do about it
All of these work from inside the app, without contacting us.
Airplane mode
Still recording
Work fully offline
Disconnect entirely and everything that matters still runs. This is the honest test of the claim.
Export audio
Within the 72h window
Take it with you
Save a recording's audio to your device any time inside its 72-hour local window. After that it's gone, on the same clock that clears it automatically.
On-device
Push to cloud anytime
Choose your sync mode
Pick On-device or Cloud when you sign in. On-device recordings stay private by default; push a single one to the cloud later if you want it there.
MCP client
Label & rename only
Revoke an assistant
Disconnect an MCP client from your dashboard at any time. Access is read-mostly — it can label and rename, never upload, record or delete.
What we don't claim
A security page that only lists strengths isn't much use to the person who has to sign off on it. So, plainly: we are a small team, and we do not hold a SOC 2 or ISO 27001 certification today. We are not going to imply otherwise with a badge.
What we offer instead is an architecture that makes most of those questions moot — audio that never transmits cannot be breached on our side — plus a direct line to the people who built it. If your review needs answers we haven't published, ask and we'll write them down.
Test the claim yourself
Install it, pull the network cable, and record a meeting. That is the whole demonstration.
Security and data handling, in full
On this page
Version 0.2.0
Download as PDFRecording stays on your device
Audio recording, transcription and speaker identification run locally in the desktop app. Your recordings are not uploaded to Cohearo for transcription or AI enhancement.
The voice embeddings used to distinguish speakers also stay on your device. If you sync speaker profiles, their identifiers and the names you assign to them can sync; the voice embeddings do not.
You choose when to use cloud features
In local mode, transcripts are stored on your device. They are not automatically uploaded when you reconnect or switch to cloud mode.
Cloud features use transcript text:
- AI enhancement: when enabled, transcript text is sent to our backend and then to our AI provider to generate the result.
- Cloud sync: transcripts sync to your account so you can access them through Cohearo's cloud features.
- Sharing and integrations: sharing content or authorizing an integration, such as an AI assistant connected through MCP, can make that content available to the people or service you authorize. Their handling of content is separate from Cohearo's AI enhancement processing.
Using an account also involves sign-in, billing and service-usage data. Diagnostics and analytics are described in our Privacy Policy, including the controls available to you. These are separate from audio recording and transcription.
AI processing and zero data retention
We use OpenRouter to route AI enhancement requests. Zero data retention is enabled on our OpenRouter account, restricting routing to endpoints that OpenRouter identifies as meeting its zero-retention policy for request content.
This setting concerns the content sent for AI processing. It does not delete transcripts you choose to store in Cohearo, or account, billing and usage records needed to operate the service. It also does not govern an external AI assistant you connect separately.
For the provider's definition and scope of this control, see OpenRouter's zero data retention documentation. Our Privacy Policy provides further information about service providers and personal data.
Storage and protection
Cohearo's production transcript storage is hosted on Amazon Web Services in São Paulo, Brazil. This storage location does not mean that all service providers process data in Brazil: external AI processing and other supporting services may operate elsewhere.
We encrypt traffic in transit and use encryption at rest for our production database and object storage. These protections are not end-to-end encryption: our services process transcript text to provide the cloud features you request.
Access controls restrict account and organization data to authorized users. Administrative functions require additional authorization, and administrator sign-in includes a second verification step. Our public API also uses edge filtering and rate limits to help reduce abusive traffic.
Security review
In August 2026, we conducted an internal application-security assessment using test accounts within and across organizations. It covered access controls and selected authentication, input-handling and integration scenarios in our development environment. The issues identified in that assessment were fixed before it was closed.
This was an internal review, not an independent penetration test or certification. Its findings apply to the version and scenarios assessed; they are not a guarantee that every vulnerability has been found. Cohearo has not been certified against SOC 2 or ISO 27001.
Questions and reporting concerns
For retention, deletion, your privacy choices and information about service providers, read our Privacy Policy.
To ask a security question or report a suspected vulnerability, email contact@cohearo.com. Describe the issue and how to reproduce it without including passwords, API keys or other people's private content.