Sloth Gist: drop in audio, video or text and get the gist, all on your own laptop

Description and use

Sloth Gist lets users locally process audio, video, and text to generate concise summaries, key points, and to‑do lists without uploading data to the cloud.

Problem

Users have large collections of voice notes, meeting recordings, lecture videos, and long articles that they never review because each item requires 10–60 minutes of manual listening or reading.

Outcome

Sloth Gist processes a folder of five MP4 demos (≈6 min audio) and a Jetpack Compose meeting note, producing concise digests with summaries, key points, and to‑do items, all without uploading data.

Workflow

• Paste file path or text into the Drop Zone
• Select Whisper model and local Ollama model from Settings
• Press "Summarize while I nap"
• The app transcribes audio/video or reads text
• Splits long recordings into 5,000‑character chunks and summarizes each
• Combines chunk summaries into final digest
• Displays one‑line summary, key points, and to‑do list for each item
• Optionally wipe saved digest

Evidence

Everything runs on my computer. Nothing is uploaded.

Source

The app refuses to talk to any model server that isn't on the same machine.

Source

Summaries are paraphrased: any line that copies six or more words in a row from the original is dropped, so the digest doesn't leak whole sentences.

Source

The app never downloads anything while it runs. You fetch the models once (ollama pull gemma3:4b) plus a one-line Whisper download, and after that it works with Wi‑Fi off.

Source