During a session
When you speak during a session, your voice is:
- Captured by your device’s microphone
- Sent to a speech recognition service to convert it to text
- The text is processed by the AI tutor to generate a response
The tutor works with the text version of what you said, not the raw audio.
After a session
Voice audio is processed in real time and is not stored permanently. The text transcript of the conversation is kept as part of your session history, but the original audio recording is not retained.
This means there are no voice recordings sitting on our servers. Only the text of what was said.
Third-party processing
Speech recognition and voice synthesis involve third-party services. These services process audio data according to their own privacy policies. Our partners are bound by data processing agreements that govern how your data is handled.