@larkup/tool-video-audio 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,63 @@
1
+ {
2
+ "$schema": "https://hub.larkup.de/schemas/tool-manifest.v1.json",
3
+ "id": "video-audio",
4
+ "name": "Video & Audio",
5
+ "description": "Index video and audio files with transcription and frame analysis.",
6
+ "longDescription": "Process long video and audio files for your knowledge base. Splits oversized Whisper uploads, captures scene-change-aware frames in a bounded pass, and supports local files, bounded direct URL downloads, and YouTube videos/playlists. Requires ffmpeg; yt-dlp is only required for YouTube URLs.",
7
+ "category": "media",
8
+ "version": "0.1.0",
9
+ "pricing": "free",
10
+ "emoji": "🎬",
11
+ "icon": "Film",
12
+ "packageName": "@larkup/tool-video-audio",
13
+ "installSize": "~15 MB",
14
+ "systemDeps": ["ffmpeg"],
15
+ "author": "Larkup",
16
+ "capabilities": [
17
+ "video-indexing",
18
+ "audio-indexing",
19
+ "transcription",
20
+ "frame-extraction",
21
+ "youtube-import"
22
+ ],
23
+ "tags": ["transcription", "ffmpeg", "video", "audio", "whisper"],
24
+ "downloads": 0,
25
+ "repositoryUrl": "https://github.com/Larkup-AI/larkup-rag",
26
+ "license": "Apache-2.0",
27
+ "updatedAt": "2026-07-20",
28
+ "configSchema": [
29
+ {
30
+ "key": "frameInterval",
31
+ "label": "Frame extraction interval (seconds)",
32
+ "type": "text",
33
+ "defaultValue": "10",
34
+ "help": "Baseline cadence for duration-aware coverage frames; scene changes and a reserved ending pass are added separately."
35
+ },
36
+ {
37
+ "key": "audioProvider",
38
+ "label": "Audio Provider",
39
+ "type": "select",
40
+ "help": "Choose the provider that should transcribe both audio files and video audio tracks.",
41
+ "options": [
42
+ { "label": "OpenAI", "value": "openai" },
43
+ { "label": "Groq", "value": "groq" },
44
+ { "label": "Deepgram", "value": "deepgram" },
45
+ { "label": "ElevenLabs", "value": "elevenlabs" },
46
+ { "label": "Local Whisper", "value": "local" }
47
+ ]
48
+ },
49
+ {
50
+ "key": "audioLanguage",
51
+ "label": "Transcription language",
52
+ "type": "text",
53
+ "defaultValue": "auto",
54
+ "help": "Use auto to infer Arabic from the media title and use provider detection otherwise. Enter a language code such as ar, ar-EG, en, or de to override it."
55
+ },
56
+ {
57
+ "key": "audioApiKey",
58
+ "label": "Audio API Key",
59
+ "type": "password",
60
+ "help": "Required for the selected provider. This key is used only by the Video & Audio tool."
61
+ }
62
+ ]
63
+ }