Auto-captions for screen recordings, without the cloud

Short answer: you don't need a cloud service, or a per-minute credit meter, to caption a screen recording. Modern speech models run on your own machine: Girato downloads a ~40MB model once, then transcribes your mic or voiceover on-device, free and unlimited, producing timed cues you can edit like text. Your audio never uploads.

Why captions matter more than ever

Most feeds autoplay muted. A demo without captions is a silent film for the majority of first-time viewers. LinkedIn, X, Reels, docs pages. Captions aren't accessibility garnish; they're the difference between "watched" and "scrolled past".

The two ways tools do this

Cloud transcription (Tella, FocuSee's AI tools, Descript): audio uploads to their servers. Quality is good; the costs are per-minute pricing, credit meters, and your voice on someone else's machine. On-device transcription (Girato): the model runs locally. First run needs internet once to fetch the model; after that it works on a plane. No meter, no upload.

How to do it in Girato

1. Record with the mic on (or upload a voiceover afterwards).
2. Open Captions → Auto-captions from mic. First run downloads the model (~40MB, once).
3. Proofread the cue list, every cue is editable text with its own timing.
4. Export. Captions render into the video, in every aspect ratio.

Tips for cleaner transcripts

• Speak a touch slower than feels natural; pause at sentence ends, the model uses silence to time cues.
• Name your product once, clearly, then correct any mishears with one edit per cue.
• Cut dead air first (Girato's silence auto-cut) so cue timing stays tight.

Frequently asked questions