Self-hosted AI video clipper (Opus Clip alternative)
Go to file
Jeff Emmett 362fe1e860 feat: add cloud AI inference support (Gemini/OpenAI-compatible)
CPU-based Ollama inference on Netcup is too slow due to server memory
pressure. Add OpenAI-compatible API support so we can use Gemini Flash
or other cloud APIs for clip analysis. Also increase transcript sample
size to 20K chars since cloud APIs handle it easily.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-10 00:44:13 +00:00
backend feat: add cloud AI inference support (Gemini/OpenAI-compatible) 2026-02-10 00:44:13 +00:00
database feat: ClipForge Phase 1 - core pipeline MVP 2026-02-08 12:27:43 +00:00
frontend feat: ClipForge Phase 1 - core pipeline MVP 2026-02-08 12:27:43 +00:00
wireguard Reverse WireGuard architecture: server on Netcup, client at home 2026-02-09 20:06:04 +00:00
.env.example feat: ClipForge Phase 1 - core pipeline MVP 2026-02-08 12:27:43 +00:00
.gitignore Add WireGuard tunnel for YouTube downloads through residential IP 2026-02-09 19:58:39 +00:00
docker-compose.yml Connect WG to traefik-public for direct Whisper access 2026-02-09 20:16:25 +00:00