Audio To Subtitle

Turn a 3-minute podcast audio clip into 1080p captioned videos just by typing what you need. Whether it's adding subtitles to audio recordings or videos or q...

Security Scan

The skill's requests and runtime instructions line up with its stated purpose (upload audio to a cloud render/transcribe service) and it only asks for a single service token; nothing requested appears disproportionate or unrelated.

Purpose & Capability

The name/description (audio → captioned video) match the instructions (upload audio, create session, transcribe, render/export). The declared primary credential (NEMO_TOKEN) is appropriate for a cloud backend API. Minor metadata inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry summary said no required config paths; this is a small mismatch in metadata but does not contradict the core purpose.

Instruction Scope

The SKILL.md explicitly describes network calls to the nemovideo API (auth, session creation, upload, SSE, render polling) and how to handle responses — all consistent with performing remote subtitle generation and video rendering. The skill will upload user files to an external service and may create an anonymous token if NEMO_TOKEN is not provided; that is expected behavior for a cloud processing skill. It also instructs deriving attribution headers and detecting install path to populate X-Skill-Platform, which requires reading the agent install path but is coherent with the stated header requirements.

Install Mechanism

Instruction-only skill with no install spec and no code files. No packages, downloads, or archive extraction are performed by the skill itself — lowest-risk install profile.

Credentials

The only required environment credential is NEMO_TOKEN, which is appropriate for authenticating to the described third-party API. The SKILL.md also describes acquiring a short-lived anonymous token if none is present; that is proportional to the service behavior. No unrelated credentials or broad system secrets are requested.

Persistence & Privilege

The skill does not request always: true and does not attempt to modify other skills or system-wide configuration. It will keep a session_id for job operations (normal for a session-based API). Autonomous invocation is allowed by default (platform norm) but is not combined with any other high-risk privilege.

Assessment

This skill will upload audio and derived media to an external service (mega-api-prod.nemovideo.ai) for transcription and rendering. That behavior is expected for the described feature, but consider data privacy before sending sensitive audio. Give the skill a dedicated NEMO_TOKEN with limited scope if possible, or test first with non-sensitive files. Note the SKILL.md can obtain an anonymous short-lived token if NEMO_TOKEN is absent—anonymous uploads still leave data on the provider. Also be aware the skill inspects the environment/install path to set an X-Skill-Platform header (it may read agent install paths); if you prefer to avoid that, do not install or run the skill. Finally, verify the provider's privacy/retention policy before sending proprietary or private recordings.

Getting Started

Share your audio files and I'll get started on subtitle generation. Or just tell me what you're thinking.

Try saying:

• "convert my audio files"
• "export 1080p MP4"
• "transcribe the audio and add subtitles"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Audio to Subtitle — Convert Audio into Captioned Videos

This tool takes your audio files and runs subtitle generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 3-minute podcast audio clip and want to transcribe the audio and add subtitles in English — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: cleaner audio with less background noise produces more accurate subtitles.

Matching Input to Actions

User prompts referencing audio to subtitle, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

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	❌

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.

Base URL: https://mega-api-prod.nemovideo.ai

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is audio-to-subtitle, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

SSE Event Handling

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

~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the export workflow

Draft field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "transcribe the audio and add subtitles in English" — concrete instructions get better results.

Max file size is 500MB. Stick to MP3, MP4, WAV, M4A for the smoothest experience.

Export as MP4 for widest compatibility across platforms.

Common Workflows

Quick edit: Upload → "transcribe the audio and add subtitles in English" → Download MP4. Takes 30-60 seconds for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.