caption-conversation
/caption-conversation
Show live, rolling captions of speech Jarvis hears — for accessibility, noisy rooms, or meetings — with optional translation. Use for "caption this", "turn on subtitles", "caption what they're saying", or "subtitle this meeting". Triggers: caption, captions, subtitles, transcribe live, what are they saying, accessibility, hard of hearing, meeting transcript.
- Author
- sumitaich1998 ↗
- Repository
- jarvisvr ↗
- Licence
- MIT
- Last repository change
- 10.06.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 10.06.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Show live, rolling captions of speech Jarvis hears — for accessibility, noisy rooms, or meetings — with optional translation. Use for "caption this", "turn on subtitles", "caption what they're saying", or "subtitle this meeting". Triggers: caption, captions, subtitles, transcribe live, what are they saying, accessibility, hard of hearing, meeting transcript.
Triggers from the description
Original author description
Show live, rolling captions of speech Jarvis hears — for accessibility, noisy rooms, or meetings — with optional translation. Use for "caption this", "turn on subtitles", "caption what they're saying", or "subtitle this meeting". Triggers: caption, captions, subtitles, transcribe live, what are they saying, accessibility, hard of hearing, meeting transcript.
How it works
- Steps
- Output
- Edge cases
SKILL.md preview
---
name: caption-conversation
description: >-
Show live, rolling captions of speech Jarvis hears — for accessibility, noisy
rooms, or meetings — with optional translation. Use for "caption this", "turn on
subtitles", "caption what they're saying", or "subtitle this meeting".
Triggers: caption, captions, subtitles, transcribe live, what are they saying,
accessibility, hard of hearing, meeting transcript.
license: MIT
compatibility: >-
Requires JarvisVR agent-backend with ambient audio (perception.audio_scene).
Protocol v1.1 §8.
metadata:
agent: communication-agent
category: communication
version: "1.0"
author: jarvisvr
allowed-tools: show_live_caption
---
# Caption Conversation
Render a `live_caption` panel that scrolls speech Jarvis hears in real time,
tagged by speaker, optionally translated.
## Steps
1. **Ensure ambient audio is on:** `perception.request{stream:"ambient_audio",
action:"start", reason:"user asked for live captions"}`.
2. **Open `show_live_caption`** with an empty/seed `lines` array and the right
`speaker` and `max_lines`.
3. **Per audio window:** append `perception.audio_scene.ambient_transcript` to
`lines` (newest last), set `speaker` (`user|other|jarvis|unknown`), and
`holo.update`. Trim to `max_lines`.
4. **Translate (optional):** if a target language is requested, translate each
line, set `translated:true` and `language` (pair with `live-translate`).
5. **Stop** captions and the audio stream when the user is done.
## Output
`live_caption` (`show_live_caption`, props per registry.json):
```json
{ "widget_type": "live_caption",
"transform": { "anchor": "head", "position": [0.0,-0.35,1.0], "billboard": true },
"props": { "lines": [ "Hello there.", "How can I help you today?" ],
"speaker": "other", "max_lines": 3, "language": "en", "translated": false },
"interactions": ["grab","tap","resize"] }
```
Update as speech arrives (`holo.update`):
```json
{ "object_id": "O_caption",
"props": { "lines": [ "How can I help you today?", "I'd like the window seat." ], "speaker": "other" } }
```
## Edge cases
- **Multiple speakers** → tag turns by `speaker`; "unknown" when diarization is
uncertain.
- **Background noise / no speech** → keep the panel idle; don't caption music or
ambient sounds (that's perception `identify_sound`).
- **Long sessions** → cap visible `lines` (`max_lines` ≤ 10); the full transcript
can be saved as a note.
- **Translated captions** → set `translated:true`; consider a two-line layout
(original + translation) via `live-translate`.
- **Privacy** → captioning others' speech is sensitive; it's user-initiated and
`perception.state` reflects active capture. Stop promptly when asked.
Versions
The database has no other skills named caption-conversation.
Database snapshot: 13.11.2026 · package version 803d7bc4e33e (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 88launch-jarvis
Launch, verify and stop this repo's read-only Jarvis dashboard. Use when the user says 'launch Jarvis', 'start Jarvis', 'open Jarvis' or 'stop Jarvis'. - 100captions-subtitles
Create, edit, translate and burn in captions and subtitles - transcribe speech with Whisper, write SRT/VTT/ASS files, style them, and hard-burn word-highlight captions for Shorts, Reels and TikTok. Use for any captioning, subtitle, transcript or accessibility request. - 100popcaps
Add animated word-by-word captions to a video with the popcaps CLI, and export SRT/VTT subtitles or a transparent caption overlay. Use when the user asks to caption or subtitle a video, add TikTok/Reels/Shorts style captions, burn in subtitles, or make captions like Submagic, Captions or CapCut. - 100word-captions
Add word-timed, TikTok-style captions to Remotion videos, from transcribing speech with faster-whisper (any language) to Caption JSON, the highlighted caption track and .srt import. Use for captions or subtitles on any video. - 100video-captions
Add burned-in captions to a video by transcribing its speech locally and placing the text in sync. The caption look defaults to a minimal, common style; the user can describe any design in plain words and it will be applied, and a built-in "pill" preset gives editorial lowercase… - 100capcut-captions
Transcribe speech in a video or audio file and produce captions or subtitles with CapCut, including SRT or VTT files. Use for "add captions", "generate subtitles", "transcribe this video" and similar requests. Do not use an AI rough cut for caption-only requests.