Skip to content
SPECIFICTION
Get listed

Sift Video

github.com

WebAPISelf-hosted
Visit github.com
Spec score 7.0 #23 of 24 in AI Video Search Tools

Spec sheet

What it does
SIFT-Video is a multimodal semantic video search engine that searches video audio and visual content with natural-language queries and returns relevant timestamps.Read 8 Oct 2026 · github.com
Purpose
SIFT-Video searches video audio and visual content with natural-language queries and returns relevant timestamps.Read 7 Oct 2026 · github.com
Audience
The README provides Docker, Git, and optional NVIDIA GPU setup instructions, and invites users to contribute issues or pull requests.Read 7 Oct 2026 · github.com
Deployment
The project runs through Docker Compose and serves its web interface at localhost:8080.Read 8 Oct 2026 · github.com
API
The REST API includes search, URL download progress, file upload, video listing and streaming, deletion, and a health endpoint.Read 8 Oct 2026 · github.com
License
The repository states that the project is licensed under GNU GPLv3.Read 8 Oct 2026 · github.com
Maker
The GitHub profile identifies the maker as Sourav Kumar.Read 8 Oct 2026 · github.com
Audio and visual search
The search interface supports all-match, audio-only, and visual-only filtering.Read 8 Oct 2026 · github.com
File uploads
The web UI accepts MP4, WebM, MKV, MOV, AVI, and OGV files up to 1 GB.Read 7 Oct 2026 · github.com
GPU support
Separate NVIDIA GPU builds can use CUDA for Whisper transcription and ONNX Runtime inference, with NVIDIA Container Toolkit required on the host.Read 8 Oct 2026 · github.com
Live ingestion
The system accepts yt-dlp-compatible URLs and streams ingestion progress while downloading, extracting frames, transcribing with Whisper, and embedding content.Read 8 Oct 2026 · github.com
Local data handling
The README describes a local Docker deployment with video and output directories and a Qdrant service; it does not state a security certification or compliance status.Read 7 Oct 2026 · github.com
Offline indexing
Videos are processed offline, with audio and frames converted into semantic embeddings and indexed in Qdrant.Read 8 Oct 2026 · github.com
Processing
Videos are processed offline, with audio and frames converted into semantic embeddings and indexed in Qdrant.Read 7 Oct 2026 · github.com
Search filters
Users can filter searches to audio, visual, or all matches and scope searches to one selected video.Read 7 Oct 2026 · github.com
Search results
Results show video names, timestamps, match types, transcript excerpts, and relevance scores, and can open the built-in player at the matching moment.Read 8 Oct 2026 · github.com
Support and contributions
The README welcomes suggestions, fixes, and improvements through issues or pull requests.Read 8 Oct 2026 · github.com
Technology
The documented stack includes Whisper small.en for timestamped speech transcription and MobileCLIP2-S3-OpenCLIP for text and image embeddings.Read 8 Oct 2026 · github.com
Upload limits
Local uploads support mp4, webm, mkv, mov, avi, and ogv files up to 1 GB.Read 8 Oct 2026 · github.com
URL ingestion
The project can download yt-dlp-compatible URLs and stream ingestion progress through server-sent events.Read 7 Oct 2026 · github.com

Where Specifiction places it

Alternatives to Sift VideoAll alternatives →