OYYO AI NotzUp: Capture All · guide
Media transcription
Run private on-device transcription for supported audio and video containing speech.
Before you begin
- An authorized audio or video file with speech, or a consented local recording.
- Compatible local speech models, sufficient device resources and support for the language and media format.
Step by step
Import speech or music
Select supported audio or video from an authorized recording or import. Native import is not limited to WAV. Music without speech is not a speech transcript.
Check local packs and languages
Finish the compatible speech-model download in the native app. Select the language or automatic/mixed-language option only when offered by that model. Language changes within a recording can affect accuracy; do not assume every language pair is supported.
Run on-device processing
Start transcription locally and keep the device awake. Where your installed engine supports them, choose offline translation or audio/music measurements from its available tasks. These are model- and device-dependent, not universal functions of the website. Noise and overlapping speech affect results; no cloud engine takes over.
Check source-grounded results
Review Transcript against playback where supported. Correct names and numbers, then check every summary and action item against the source. Translations and measurements need review too; generated results are not verified facts.
Edit or export
Use the file workspace tabs to edit, copy or share a section and export the formats offered for that section.
Expected result
An editable transcript and reviewed summary/actions for media with speech; silent media does not produce speech text.
Privacy and permissions
Recordings, files, searches, scans, OCR, barcode counts and supported local-AI results do not leave the device by default. Only a deliberate online action—Share, Search online, connector authorization or encrypted backup—transmits the selected data or value. Language-pack downloads do not upload the source text. Files, recordings, scans, local searches and local-AI results stay on your device by default. All inference runs on your own awake, authorized device, with no cloud AI, hidden cloud processing or remote fallback. You choose what to share, with whom, in which format and when. Online searches, connectors, sharing and optional backup transmit the data needed for the action you explicitly choose.
Troubleshooting
No transcript
Confirm the file actually has an audible speech track, then check codec, model and language support. Use Visual analysis for silent video.
Processing is slow or inaccurate
Keep the device awake, free resources and use clearer audio or a suitable supported model. Review output manually; automatic text is not a verified record.