Official documentation
YapRun Privacy Policy
RunAnywhere AI, 2026
Read the originalRead on October 23, 2026
- What it is
- YapRun's privacy policy, effective February 23, 2026, from RunAnywhere AI. It says audio is processed on the device and discarded, that no audio is sent to any server, and that the text stays on the device. Its only network use is SDK setup and model downloads.
- How much weight it carries
- The maker's own policy, read in October 2026. It describes the app's own design and says nothing about model training. The no-training row rests on its statement that no audio is recorded or stored.
Facts taken from this source
- YapRun's privacy policy says it does not transmit audio to any server and that transcription runs on the device.
“We do NOT transmit audio to any server. Transcription runs entirely on your device using Apple's Neural Engine or CPU. No audio data is sent over the internet.” (Section 2, Information We Do NOT Collect)
- YapRun's privacy policy says it does not record or store audio and discards it after transcription.
“We do NOT record or store your audio. Audio captured by the microphone is processed in real-time by on-device AI models and immediately discarded after transcription.” (Section 2, Information We Do NOT Collect)
- YapRun's privacy policy says the text generated from your voice stays on your device.
“The text generated from your voice stays on your device. We have no access to it.” (Section 2, Information We Do NOT Collect)
- YapRun's privacy policy says audio is processed locally by an on-device AI model.
“Audio is processed locally by the on-device AI model (WhisperKit on Neural Engine or ONNX on CPU).” (Section 4, Microphone Access)
- YapRun's privacy policy says that after the initial model download, the app works fully offline.
“After the initial model download, YapRun works fully offline” (Section 6, Network Usage)