Sondo Ai

Turn a 2-minute interview recording with background noise into 1080p clean audio videos just by typing what you need. Whether it's removing background noise...

Security Scan

The skill's requests and runtime instructions are consistent with an AI cloud audio/video processing service, but it will upload your media and contact an external API (including acquiring anonymous tokens), so review privacy before use.

Purpose & Capability

The skill claims to perform cloud-based audio/video cleanup and only requires a NEMO_TOKEN (or will acquire an anonymous one). Required items (token, session, uploads) align with the stated cloud render purpose; no unrelated credentials or binaries are requested.

Instruction Scope

Instructions focus on creating a session, streaming edits over SSE, uploading video files (via multipart or URL), polling render status, and returning download URLs—all appropriate for the service. Two things to note: (1) the skill will POST files from provided local paths (it expects uploaded files), so any local file path you provide will be read and transmitted to the remote service; (2) it instructs detecting install paths (e.g., ~/.clawhub/, ~/.cursor/skills/) to set an X-Skill-Platform header, which implies checking for certain filesystem paths. Both are explainable by the skill's telemetry/attribution needs but are material to privacy.

Install Mechanism

No install spec or downloaded code — instruction-only. That minimizes on-disk code execution risk.

Credentials

Only NEMO_TOKEN is declared as required and is the primary credential; this matches the API usage. The metadata also references a config path (~/.config/nemovideo/) and the runtime will optionally obtain an anonymous token if NEMO_TOKEN is absent — reasonable but worth noting if you expect the skill not to contact the backend without an explicit token.

Persistence & Privilege

Skill is not marked always:true and is user-invocable; it does not request elevated or persistent platform privileges nor modify other skills. Normal autonomous invocation applies.

Scan Findings in Context

[NO_CODE_FILES] expected: The static scanner had no code files to analyze because this is an instruction-only skill (SKILL.md). No regex-based findings were produced; the runtime behavior is described entirely in prose.

Assessment

This skill will upload any video files you provide to mega-api-prod.nemovideo.ai and may automatically obtain an anonymous token if you don't set NEMO_TOKEN. Before installing or using it: (1) do not upload sensitive or private media unless you trust the remote service and have verified its privacy/retention policy; (2) if you prefer control, set your own NEMO_TOKEN rather than allowing anonymous-token acquisition; (3) be aware it may inspect certain local paths to populate an X-Skill-Platform header (this is attribution/telemetry, not credential theft, but it does involve checking for directories); (4) confirm the external domain and service terms if provenance matters. Overall the skill's behavior is coherent with its stated purpose, but the privacy implications of remote processing are the primary thing to consider.

Getting Started

Share your video clips and I'll get started on AI sound editing. Or just tell me what you're thinking.

Try saying:

• "enhance my video clips"
• "export 1080p MP4"
• "remove background noise and enhance voice"

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.

Sondo AI — AI Audio Cleanup for Videos

Send me your video clips and describe the result you want. The AI sound editing runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a 2-minute interview recording with background noise, type "remove background noise and enhance voice clarity", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: shorter clips under 60 seconds process significantly faster.

Matching Input to Actions

User prompts referencing sondo 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is sondo-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).

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.

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.

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.

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 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)

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

Common Workflows

Quick edit: Upload → "remove background noise and enhance voice clarity" → 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 "remove background noise and enhance voice clarity" — 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.