Video Transcription Free

students, content creators, podcasters convert video files into captioned text videos using this skill. Accepts MP4, MOV, AVI, WebM up to 500MB, renders on c...

Security Scan

The skill's declared purpose (video → captions) matches most instructions, but there are provenance and scope inconsistencies (unknown source, frontmatter asking to read config/install paths) that warrant caution before installing or using it with sensitive files or credentials.

Purpose & Capability

The skill's name/description align with the actions described (upload video, transcribe, render MP4). Requiring a single API token (NEMO_TOKEN) is reasonable. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata reported no required config paths—this mismatch and the missing homepage/unknown source reduce trust in provenance.

Instruction Scope

Runtime instructions direct the agent to perform network calls to https://mega-api-prod.nemovideo.ai, upload local files (multipart -F "files=@/path"), generate anonymous tokens, and 'detect' install-paths to set an X-Skill-Platform header (reading ~/.clawhub, ~/.cursor/skills/ etc.). Detecting install paths or reading a config directory implies the skill may probe the user's filesystem; that is broader in scope than mere file upload/transcription and could expose sensitive data if performed indiscriminately.

Install Mechanism

This is an instruction-only skill with no install spec or code files; nothing will be written to disk by an installer. That lowers installation risk.

Credentials

Only NEMO_TOKEN is declared as required, which is appropriate for a remote API. But the SKILL.md also documents an anonymous-token flow (so an env var may be optional) and its frontmatter references a config path that could contain other credentials. The presence of an undeclared config path in the skill content is disproportionate unless the skill actually needs to read prior configuration—this should be clarified.

Persistence & Privilege

always:false and default agent-invocation behavior are normal. The skill instructs saving a session_id returned by the API; that is typical for session-based services. There is no request for persistent local installation or modification of other skills.

What to consider before installing

This skill generally does what it says (upload video to a remote API and return a rendered MP4), but exercise caution: the package has no homepage or identifiable owner, and the instructions ask the agent to probe install/config paths (e.g., ~/.config/nemovideo/, ~/.clawhub/) which could access unrelated files. Before installing or using it: 1) verify the API domain and service reputation (mega-api-prod.nemovideo.ai) and ask the publisher for a homepage or documentation; 2) avoid uploading sensitive videos or including system credentials; 3) decline filesystem probing—ask the skill to only use explicit file paths you provide; and 4) prefer using an account-bound API token you control rather than allowing anonymous-token generation. If you need higher assurance, request the skill author to remove the install-path/config probing and to publish source or official docs.

Getting Started

Send me your video files and I'll handle the AI speech transcription. Or just describe what you're after.

Try saying:

• "convert a 10-minute interview recording into a 1080p MP4"
• "transcribe the spoken dialogue into text and add captions"
• "converting spoken video audio into readable captions or text transcripts for students, content creators, podcasters"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

Video Transcription Free — Transcribe Video Speech to Text

Send me your video files and describe the result you want. The AI speech transcription runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 10-minute interview recording, type "transcribe the spoken dialogue into text and add captions", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: shorter clips under 5 minutes transcribe with higher accuracy.

Matching Input to Actions

User prompts referencing video transcription free, 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.

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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: video-transcription-free
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

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

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

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.

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 spoken dialogue into text and add captions" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 for widest compatibility across platforms and devices.

Common Workflows

Quick edit: Upload → "transcribe the spoken dialogue into text and add captions" → Download MP4. Takes 1-2 minutes 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.