Live Translation Privacy: What "No Audio Stored" Actually Means
"No audio stored" means speech is held in memory only for as long as it takes to transcribe and translate it, then discarded — nothing is written to disk, and there's no recording to request, leak, or subpoena later, because it never existed as a file.
The distinction that matters
There's a meaningful difference between "we don't share your recordings" and "there are no recordings." The first is a policy — a promise about what's done with data that still exists somewhere. The second is an architectural fact: if audio is processed in a streaming pipeline and never written to a file or database, there's no recording to have a policy about in the first place.
For a conversation tool specifically, this matters because live conversations are often more sensitive than the documents people are usually careful about — a live meeting can include anything said in the room, not just what someone deliberately chose to write down.
What is kept, if anything
The translated text itself is a separate question from the audio, and reasonable products differ here: some keep no transcript at all beyond what's on screen during the session, others let a signed-in user explicitly choose to save a session's text afterward. The useful question to ask any tool isn't just "is audio stored" but "what exactly persists, for how long, and does that require me to opt in" — text a user explicitly chose to save is a very different thing from audio retained by default.
Be first to try real-time interpretation yourself.
In active testing — join the waitlist and we'll email you when it's ready.
Read next
What Is Real-Time Speech Translation, and How Is It Different From an Interpreter App?
Real-time speech translation listens to speech as it's spoken and produces translated text (and often audio) within a few seconds — continuously, not after you finish a sentence and hit a button.
Simultaneous Interpretation for Video Calls: How It Actually Works
On a video call, simultaneous interpretation is a short pipeline running continuously in the background: audio in, transcribed speech, translated text, and captions or synthesized speech out — fast enough that it never asks the conversation to pause and wait for it.
Chinese–English Interpretation: Why Simultaneous Translation Is Uniquely Hard
Chinese and English put information in different places in a sentence — Chinese often saves the key verb or qualifier for later than English would — which means a simultaneous system sometimes has to wait for more of a Chinese sentence before it can commit to an English translation, or vice versa.