T
Settings
Gallery
Mindmap
Search
Bookmarks
Trails
Admin
Failed
Saved Lists
Jobs
Settings
Whisper Transcription
Model
tiny
base
small
medium
large-v2
large-v3
Larger models are more accurate but slower. "medium" is a good default for GPU.
Device
GPU (CUDA)
CPU
Compute Type
float16
int8_float16
int8
float32
float16 for GPU, int8 for CPU.
LLM Summary (Optional)
Provider
None (extractive summary)
OpenAI
Anthropic
Gemini (Google)
Ollama (local)
Model Name
Leave blank for provider default. API keys come from .env (OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, or legacy LLM_API_KEY). Ollama needs no API key. Reprocess picker in the gallery only offers providers whose keys are set.
Ollama URL
Only used when provider is Ollama. Default works for Docker Desktop (Mac/Windows). On Linux use
http://172.17.0.1:11434
or your host IP.
LLM transcript cleanup (typos, punctuation, obvious misheard words; preserves meaning)
Adds a "Transcript (Corrected)" section to every markdown file. Disable if LLM cost is a concern.
Submission Pipeline
Auto-transcribe videos on submit
When off, videos submitted via the extension are only downloaded. Use the gallery to select which ones to transcribe. Useful when your library is large and whisper is the bottleneck.
Auto-cleanup
Auto-move completed saved videos
After a saved-list video finishes transcribing, move it to the list below. The next extension poll handles the move (non-destructive).
Target list name
The Instagram saved list the extension will move transcribed videos into. Created automatically if it does not exist.
Transcript Storage
Save transcripts to
Local filesystem (./data/transcripts/)
Google Drive
Local saves markdown files to the mounted data volume. Google Drive requires a connected Google account.
Google Drive Root Folder
Only used when storage is set to Google Drive.
Save settings