Video To Text Japanese

Turn a 3-minute Japanese interview recording into 1080p Japanese text transcripts just by typing what you need. Whether it's transcribing Japanese video spee...

Security Scan

The skill's requirements and runtime instructions are generally consistent with a cloud-based Japanese video transcription service and request only a single API token, but there are minor metadata mismatches and some vague filesystem/attribution behavior to be aware of.

Purpose & Capability

The skill claims to transcribe Japanese video and its runtime instructions only require a single service token (NEMO_TOKEN) and calls to a Nemovideo API — this is proportionate to the stated purpose. Note: the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) which conflicts with the registry metadata that listed no required config paths.

Instruction Scope

Instructions stay within the service's domain (upload, session creation, SSE, render/export). They instruct the agent to use NEMO_TOKEN (or acquire an anonymous token from the service) and to persist session_id. There is some vagueness: attribution headers are derived from YAML frontmatter and install-path detection (~/.clawhub, ~/.cursor/skills/), which implies the agent may try to inspect installation paths; the doc does not clearly define where session_id is stored.

Install Mechanism

No install spec or code files are present (instruction-only), so nothing is downloaded or written by an install step — lowest install risk.

Credentials

Only one environment credential is required (NEMO_TOKEN), which is appropriate for an API-backed transcription service. The SKILL.md frontmatter references a config path (~/.config/nemovideo/) not declared elsewhere — this is a minor inconsistency but does not by itself indicate excessive credential access.

Persistence & Privilege

The skill does not request always:true and does not ask to modify other skills or system-wide settings. It instructs the agent to store session_id for ongoing jobs, which is reasonable for long-running cloud renders.

Assessment

This instruction-only skill appears to be what it claims: a cloud transcription/render front-end that talks to https://mega-api-prod.nemovideo.ai and requires a NEMO_TOKEN. Before using it: (1) Only provide a NEMO_TOKEN you trust — if you let the skill request an anonymous token, that token grants the remote service permission to process your uploads for 7 days. (2) The skill will upload video content to an external service — do not upload sensitive or private recordings unless you trust Nemovideo's policies. (3) The SKILL.md mentions a local config path and asks the agent to detect install paths; confirm your agent will not expose unrelated local files. (4) There is no install script to review (behavior is driven by SKILL.md), so verify the remote API domain and privacy/terms before proceeding. If you need stronger assurance, ask the publisher for a homepage, docs, or a vetted service account rather than allowing anonymous token creation.

Getting Started

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

Try saying:

• "convert a 3-minute Japanese interview recording into a 1080p MP4"
• "transcribe this Japanese video into text with timestamps"
• "transcribing Japanese video speech into readable text for students, translators, content creators"

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 to Text Japanese — Transcribe Japanese Video to Text

Drop your video files in the chat and tell me what you need. I'll handle the Japanese transcription generation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a a 3-minute Japanese interview recording, ask for transcribe this Japanese video into text with timestamps, and about 1-2 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — cleaner audio with less background noise produces more accurate Japanese transcriptions.

Matching Input to Actions

User prompts referencing video to text japanese, 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.

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is video-to-text-japanese, 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).

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

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute export workflow

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

Draft JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

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 this Japanese video into text with timestamps" — concrete instructions get better results.

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

MP4 with clear mono or stereo audio gives the best transcription accuracy.

Common Workflows

Quick edit: Upload → "transcribe this Japanese video into text with timestamps" → 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.