Vozo Ai

Cloud-based vozo-ai tool that handles editing and enhancing voiceovers in video content. Upload MP4, MOV, AVI, WebM files (up to 500MB), describe what you ne...

Security Scan

The skill's requirements and instructions are consistent with a cloud video/voice-editing tool: it needs a NEMO_TOKEN (or will obtain an anonymous one), uploads video files to a nemovideo.ai backend, and does not request unrelated credentials or install anything locally.

Purpose & Capability

Name/description match the declared API endpoints and required NEMO_TOKEN. Declared config path (~/.config/nemovideo/) and primaryEnv NEMO_TOKEN are coherent for a client of the stated cloud service.

Instruction Scope

The SKILL.md instructs the agent to automatically obtain an anonymous token if NEMO_TOKEN isn't set, create sessions, upload user video files (up to 500MB), stream SSE events, and poll render status. These behaviors are expected for this functionality, but they mean user media will be sent to an external endpoint (mega-api-prod.nemovideo.ai). The file upload and automatic token acquisition are explicit in the instructions.

Install Mechanism

No install spec and no code files — instruction-only. That minimizes on-disk risk; nothing is downloaded or installed by the skill itself.

Credentials

Only NEMO_TOKEN is required (primary credential). The config path listed is relevant to the service. No unrelated secrets or multiple credentials are requested.

Persistence & Privilege

always:false and normal autonomous invocation. The skill does not request persistent system privileges or to modify other skills. It may detect install paths and read the declared config directory to find existing tokens/configs, which is reasonable for a client.

Assessment

This skill will upload your video files and interact with an external service at mega-api-prod.nemovideo.ai; if you care about privacy or confidentiality, do not upload sensitive footage. The skill will use NEMO_TOKEN if provided, or automatically request an anonymous token (100 free credits, 7-day expiry) — be aware the agent will perform network calls to obtain and use that token. Only provide a NEMO_TOKEN you trust and avoid giving broader credentials. The skill may read ~/.config/nemovideo/ and check install paths to set headers — if those locations contain sensitive data, remove it before using the skill. If you want extra caution, test with a short non-sensitive clip first and verify the service/domain independently (privacy policy, retention) before uploading production content.

Getting Started

Got video clips to work with? Send it over and tell me what you need — I'll take care of the AI voice editing.

Try saying:

• "edit a 2-minute talking-head video recording into a 1080p MP4"
• "change the speaker's voice tone and remove filler words automatically"
• "editing and enhancing voiceovers in video content for content creators"

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.

Vozo AI — Edit Voice Audio in Videos

This tool takes your video clips and runs AI voice editing through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 2-minute talking-head video recording and want to change the speaker's voice tone and remove filler words automatically — the backend processes it in about 30-60 seconds and hands you a 1080p MP4.

Tip: shorter clips under 60 seconds process significantly faster and use fewer credits.

Matching Input to Actions

User prompts referencing vozo ai, 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is vozo-ai, 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

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

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)

Common Workflows

Quick edit: Upload → "change the speaker's voice tone and remove filler words automatically" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "change the speaker's voice tone and remove filler words automatically" — 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.