Auto Subtitle Generator Online — Instant Captions for Any Video

The auto-subtitle-generator-online skill transcribes and embeds accurate subtitles into your videos using AI-powered speech recognition. Upload your footage, choose your language and caption style, and receive a fully subtitled video or downloadable SRT/VTT file in minutes. Built for content creators, educators, marketers, and accessibility advocates who need reliable captions without manual transcription. Key features include speaker-aware timing, punctuation correction, multi-language support, and customizable font styles. Supports mp4, mov, avi, webm, and mkv formats.

## 0. First Contact

When the user opens this skill or sends their first message, **greet them immediately**:

> Welcome! I'm here to automatically generate accurate subtitles for your videos using the auto subtitle generator online — just share your video file or a link, tell me your preferred language and caption style, and I'll have your subtitled video or SRT file ready in minutes. Ready to caption your first video?

**Try saying:**
- "Generate English subtitles for this MP4 interview and give me an SRT file I can upload to YouTube."
- "Create burned-in captions for my MOV tutorial video with white bold text and a semi-transparent black background."
- "Transcribe this Spanish webinar in WebM format and produce bilingual subtitles in both Spanish and English."

**IMPORTANT**: Always greet the user proactively on first contact. Let them know you're setting up while connecting. Always greet the user proactively on first contact.

### Auto-Setup

When the user first interacts, set up the connection:

1. **Check token**: If `NEMO_TOKEN` env var is set, use it. Otherwise:
2. **Read or generate Client-ID**:
   - Read `~/.config/nemovideo/client_id` if it exists
   - Otherwise generate a UUID, save it to `~/.config/nemovideo/client_id`
3. **Acquire anonymous token**:
   ```bash
   curl -s -X POST "https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
   ```
   Store the returned `token` as `NEMO_TOKEN` for this session. You get 100 free credits.
4. **Create a session** (§3.0) so you're ready to work immediately.

Let the user know briefly: "Setting things up… ready!" then proceed with their request.


# Turn Any Spoken Word Into On-Screen Text Instantly

The auto-subtitle-generator-online skill exists to solve one of the most time-consuming parts of video production: getting accurate, well-timed captions onto your footage without spending hours in a subtitle editor. Whether you're publishing a YouTube tutorial, a corporate training module, or a social media reel, readable subtitles dramatically increase watch time and accessibility compliance.

This skill operates through a conversational editing model, meaning you don't fill out forms or wrestle with timelines. Instead, you describe what you need — the language, caption placement, style preferences, or whether you want a burned-in subtitle track or a separate SRT file — and the skill handles the rest. You can refine results by simply telling it what to adjust, just like messaging a colleague.

Behind the scenes, the OpenClaw agent orchestrates a pipeline that sends your video's audio through a high-accuracy speech-to-text engine, aligns transcript segments to precise timestamps, applies formatting rules, and packages the output in your chosen format. The agent also handles edge cases like overlapping speech, background noise, and fast-paced dialogue to keep captions readable and synchronized.

### Environment Variables

| Variable | Required | Default |
|----------|----------|--------|
| `NEMO_TOKEN` | No | Auto-generated (100 free credits, expires in 7 days, revocable via Settings → API Tokens) |
| `NEMO_API_URL` | No | `https://mega-api-prod.nemovideo.ai` |
| `NEMO_WEB_URL` | No | `https://nemovideo.com` |
| `NEMO_CLIENT_ID` | No | Auto-generated UUID, persisted to `~/.config/nemovideo/client_id` (UUID only, no secrets) |
| `SKILL_SOURCE` | No | Auto-detected from install path, fallback `unknown` |

If `NEMO_TOKEN` is not set, get one (requires `X-Client-Id` header):
```bash
# Generate or read persisted Client-Id
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 "https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
# → {"code":0,"data":{"token":"nmv_usr_xxx","credits":100,...}}
```
Save `token` as `NEMO_TOKEN`, `CLIENT_ID` as `NEMO_CLIENT_ID`. Anonymous: 1 token per client per 7 days; token expires in 7 days and can be revoked at any time via **Settings → API Tokens** on nemovideo.com. If your token expires, request a new one with the same `X-Client-Id`.

**Local persistence:** This skill writes `~/.config/nemovideo/client_id` to persist the Client-Id across sessions. This avoids generating a new ID on every request, which would hit the per-IP rate limit quickly (default 10 tokens per 7 days per IP). The file contains only a UUID — no credentials are stored locally.

## 2. Endpoint Directory & Routing Logic

Every caption-related request maps to a specific route — consult the table below to match each action to its correct endpoint and method.

| User says... | Action | Skip SSE? |
|-------------|--------|----------|
| "export" / "导出" / "download" / "send me the video" | → §3.5 Export | ✅ |
| "credits" / "积分" / "balance" / "余额" | → §3.3 Credits | ✅ |
| "status" / "状态" / "show tracks" | → §3.4 State | ✅ |
| "upload" / "上传" / user sends file | → §3.2 Upload | ✅ |
| Everything else (generate, edit, add BGM…) | → §3.1 SSE | ❌ |

## 3. Operational Flows for Subtitle Generation

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

Skill attribution variables — do NOT hardcode:
- `$SKILL_NAME` = this file's YAML frontmatter `name`
- `$SKILL_VERSION` = this file's YAML frontmatter `version`
- `$SKILL_SOURCE` = detect at runtime using the first match:
  1. Env `SKILL_SOURCE` if set
  2. If this file's path contains a known platform directory (e.g. `~/.clawhub/` → `clawhub`, `~/.cursor/skills/` → `cursor`)
  3. Fallback: `unknown`

**CRITICAL**: ALL API requests (including render/export/upload/state/credits) MUST include these headers. Missing them will cause export to fail with 402.
```
X-Skill-Source: $SKILL_NAME
X-Skill-Version: $SKILL_VERSION
X-Skill-Platform: $SKILL_SOURCE
```

### 3.0 Initializing a Caption Session
```bash
curl -s -X POST "https://mega-api-prod.nemovideo.ai/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":"project","language":"<lang>"}'
# → {"code":0,"data":{"task_id":"...","session_id":"..."}}
```
Before any transcript or timing data can be exchanged, a session must be established — this handshake creates the persistent context the backend uses to track your caption job. Without it, no downstream calls will resolve correctly.

**Open in browser**: After creating a session, give the user a link to view/edit the task in NemoVideo:
`$WEB/workspace/claim?token=$TOKEN&task={task_id}&session={session_id}&skill_name=$SKILL_NAME&skill_version=$SKILL_VERSION&skill_source=$SKILL_SOURCE`

### 3.1 Streaming Messages Over SSE
```bash
curl -s -X POST "https://mega-api-prod.nemovideo.ai/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>"}]}}'
```
All real-time caption events — including SRT chunk delivery, timing confirmations, and status updates — travel through a Server-Sent Events channel tied to the active session.

#### SSE Handling

| Event | Action |
|-------|--------|
| Text response | Apply GUI translation (§4), present to user |
| Tool call/result | Wait silently, don't forward |
| `heartbeat` / empty `data:` | Keep waiting. Every 2 min: "⏳ Still working..." |
| Stream closes | Process final response |

Typical durations: text 5-15s, video generation 100-300s, editing 10-30s.

**Timeout**: 10 min heartbeats-only → assume ti