Klaket v0.7.1

Patch release on top of the v0.7.0 launch.

Changes

• New klaket CLI in the Python package: klaket ingest <url> --wait, status, result, search, delete, usage (configure with KLAKET_API_URL / KLAKET_API_KEY)
• Friendly error message when the API is unreachable (instead of a raw traceback)
• translate_to supported in both SDK ingest() calls; JS SDK gains usage()
• JS SDK is published as klaket-sdk on npm (npm name-similarity rules); Python stays pip install klaket, MCP stays npx klaket-mcp
• Language-neutral naming for the diacritic-insensitive search internals; docs and examples generalized
• Fresh README demo GIF recorded from the dashboard with a real job

Install

pip install klaket        # Python SDK + CLI
npm i klaket-sdk          # JS/TS SDK
claude mcp add klaket -- npx klaket-mcp

Klaket v0.7.0 — first public release

The first public release of Klaket — turn any video into LLM-ready data.

Highlights

• Transcripts in ~100 languages with word-level timestamps (faster-whisper), per-job model selection and context prompts
• Speaker diarization — local & keyless (sherpa-onnx), with word-level splitting and blip smoothing
• Scene detection + keyframes (PySceneDetect AdaptiveDetector) and on-screen text OCR (RapidOCR)
• Auto chapters, SRT/VTT subtitles and local subtitle translation (Argos) — no external APIs
• In-video search: diacritic-insensitive, prefix-aware, typo-tolerant
• Playlist ingest, batch mode, webhooks, audio-only (podcast) support
• MCP server so coding agents can "watch" videos, plus Python/JS SDKs and LangChain/LlamaIndex loaders
• React dashboard with a click-to-seek playground
• One-command self-host: docker compose up --build — no API keys, no GPUs required

Quality gates

• 20-check end-to-end suite (make e2e), Go + Python unit tests in CI
• Battle-tested against real YouTube videos (AV1 normalization, hallucination guards, WER-measured accuracy)