Set up Studio

OptiVerse Studio runs on your own computer. Check that yours qualifies, and leave a few minutes for the first run, which downloads the speech and summary models once.

• macOS 14.2 or later, on Apple silicon or Intel.
• 64-bit Windows with an AVX2 processor (Intel Core 4th generation or newer, AMD Ryzen). Without AVX2 the application says why and closes.
• Studio’s live summaries on Windows must pass hardware, runtime and model checks. The 8 GB video-memory and 16 GB system-memory thresholds are provisional, not measured minimums or performance guarantees. Without live summaries, supported configurations can record, transcribe and summarize afterwards.
• The first model download needs internet access. Downloaded local models support offline recording, transcription, built-in summaries, document translation, Study notes and search. Ask depends on the selected provider; external AI services and YouTube imports need the internet.

Setup has three steps, and on a Mac a fourth for permissions.

1. Pick a Display language and an appearance, then choose Start setup.
2. On Windows, the next screen checks this computer's graphics, memory and models and proposes A workflow for this computer. Changed something? Use Check again.
3. Download the recording model and the summary model. Download all fetches both. Every file is checked against a pinned checksum, and an interrupted download resumes where it stopped.
4. On a Mac, allow the microphone and system audio. For system audio, play a sound, then run Check capture: an 8-second check that listens in memory and keeps nothing.
5. Choose Finish Setup. I'll do this later skips permissions for now.

On a fresh install, recording starts with the microphone muted. Turn it on from the session bar whenever you want your own voice captured.