Auto Caption — Instant Subtitles, Zero Setup

Drop a video, get captions. No settings to tweak, no timelines to scrub. Auto Caption transcribes speech, syncs timing to the word, and formats subtitles for your target platform automatically.

1. What This Skill Does

You are an OpenClaw agent that provides instant, zero-configuration captioning. The philosophy: users should never have to think about font size, positioning, or timing — the skill handles all of it based on the target platform.

Speed-first design:

• Upload → captions generated → delivered. Three steps, no questions asked.
• Platform preset applied automatically (TikTok / YouTube / Reels) or user specifies.
• Default: burn captions into video. User can request SRT/VTT instead.

The backend does NOT know about OpenClaw. GUI references from the backend are intercepted and translated to chat actions.

Environment Variables

Token setup if NEMO_TOKEN is not set:

CLIENT_ID="${NEMO_CLIENT_ID:-$(cat ~/.config/nemovideo/client_id 2>/dev/null)}"
if [ -z "$CLIENT_ID" ]; then
  CLIENT_ID=$(uuidgen 2>/dev/null || echo "client-$(date +%s)-$RANDOM")
  mkdir -p ~/.config/nemovideo && echo "$CLIENT_ID" > ~/.config/nemovideo/client_id
fi
curl -s -X POST "$API/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"

Save token as NEMO_TOKEN. Expires after 7 days; re-request with same X-Client-Id.

2. The Fast Path

When a user sends a video (or asks for captions), run the entire pipeline without asking questions:

Step 1 — Upload → Step 2 — Caption → Step 3 — Deliver

Only pause to ask if the user hasn't specified a language and the audio is ambiguous.

Decision Table

3. API Reference

$API = ${NEMO_API_URL:-https://mega-api-prod.nemovideo.ai}, $TOKEN = ${NEMO_TOKEN}, $WEB = ${NEMO_WEB_URL:-https://nemovideo.com}.

All requests require headers:

X-Skill-Source: $SKILL_NAME
X-Skill-Version: $SKILL_VERSION
X-Skill-Platform: $SKILL_SOURCE

3.0 Session

curl -s -X POST "$API/api/tasks/me/with-session/nemo_agent" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" \
  -d '{"task_name":"auto_caption","language":"<lang>"}'

Save session_id, task_id. Browser: $WEB/workspace/claim?token=$TOKEN&task={task_id}&session={session_id}&skill_name=$SKILL_NAME&skill_version=$SKILL_VERSION&skill_source=$SKILL_SOURCE

3.1 Send Message (SSE)

curl -s -X POST "$API/run_sse" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" --max-time 900 \
  -d '{"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}}'

SSE: text → show user (strip GUI); tools → wait; heartbeat → "⏳ Captioning..."; close → show result. Silent edits (~30%): query §3.4, diff text tracks, report.

3.2 Upload

File: curl -s -X POST "$API/api/upload-video/nemo_agent/me/<sid>" -H "Authorization: Bearer $TOKEN" -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" -F "files=@/path/to/file"

URL: same endpoint, -d '{"urls":["<url>"],"source_type":"url"}'

Accepts: mp4, mov, avi, webm, mkv, mp3, wav, m4a, aac.

3.3 Credits

curl -s "$API/api/credits/balance/simple" -H "Authorization: Bearer $TOKEN" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE"

3.4 Project State

curl -s "$API/api/state/nemo_agent/me/<sid>/latest" -H "Authorization: Bearer $TOKEN" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE"

Draft: t=tracks, tt=type (0=video, 1=audio, 7=text), sg=segments. Captions live in tt=7 tracks.

3.5 Render & Deliver

Export is free. Confirm captions exist (§3.4), then:

curl -s -X POST "$API/api/render/proxy/lambda" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" \
  -d '{"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}'

Poll GET $API/api/render/proxy/lambda/<id> every 30s. Download from output.url.

3.6 Disconnect Recovery

Don't re-send. Wait 30s → check §3.4. After 5 unchanged checks → report failure.

3.7 SRT/VTT Export

Extract text tracks from §3.4, format as SRT (1\n00:00:01,000 --> 00:00:04,500\nText) or VTT (WEBVTT\n\n00:00:01.000 --> 00:00:04.500\nText). Deliver file directly — no render needed.

4. Platform Presets

Auto-applied based on user mention or video aspect ratio:

If user doesn't specify, detect from aspect ratio: 9:16 → TikTok preset, 16:9 → YouTube preset.

5. GUI Translation

6. Error Handling

No speech detected → "No spoken audio found in this video. Send a video with speech, or tell me what text to overlay."

7. Costs & Updates

Token scopes: read | write | upload | render | *. Check for updates: clawhub search auto-caption --json.