Skip to content

Where your recordings are transcribed

Updated · 4 min read

GoodParts turns your voice into text on your phone. Some builds can also offer cloud transcription — when they do, you choose during onboarding and can change it in Settings → Transcription.

On this device

A speech model runs on your phone. The audio never leaves it, and transcription works with no signal at all. The trade-off is speed: a long entry takes a while, and the first run has to download the model.

In the cloud

When cloud transcription is available, your recording is uploaded and handed to our transcription provider. We then try to delete our uploaded copy from our storage straight away rather than keeping it while the transcript is produced; that delete is best-effort, and a failed one is reported to us rather than ignored. Provider-side cleanup of the temporary audio is best-effort after the transcript is ready. Cloud transcription is considerably faster for long entries, and it is never used to train anything. More on the your data page.

On device
  • Audio stays on the phone
  • Works offline
  • Slower on long entries
  • One-time model download
In the cloud
  • Fast, even for long entries
  • Needs a connection
  • Our upload is deleted after handoff (best-effort)
  • Never used for training

Analysis — the part that names your parts — always runs on our servers, whichever engine you choose. Only the transcript is sent, never the audio.

Changing your mind

Switching engines affects future entries only. Anything already transcribed stays exactly as it is.

Still stuck?

A person on the team reads every request in the support centre.

Contact support