Audio Upload Aioz

Turn a 3-minute MP3 podcast recording into 1080p audio-driven MP4 just by typing what you need. Whether it's uploading audio files to create shareable video...

Security Scan

The skill's declared purpose (convert/upload audio to a remote render service) matches most of its instructions, but there are inconsistencies and a couple of privacy/scope concerns (notably a mismatched config-path requirement in the frontmatter and instructions that read local paths/metadata) that you should understand before installing.

Purpose & Capability

The name/description (audio → video via AIOZ/NEMO backend) aligns with the runtime instructions that upload files and call a remote render API using a NEMO_TOKEN. However the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) that the registry metadata did not list as required; that discrepancy is unexplained and worth clarifying.

Instruction Scope

Instructions direct the agent to: use or set the NEMO_TOKEN env var, POST to an anonymous-token endpoint to obtain a token if none exists, create/save a session_id, send SSE and multipart uploads (including local file paths), and detect an install path to set X-Skill-Platform. Reading install path and the frontmatter at runtime implies filesystem access. These actions are broadly consistent with a remote-render service, but the runtime requirement to inspect local paths/config and to persist session state is scope-creeping relative to a simple 'upload/convert' helper and should be confirmed.

Install Mechanism

This is instruction-only (no install spec, no code files). That minimizes on-disk installation risk — the skill runs API calls and reads local files as described rather than installing binaries.

Credentials

The only declared required env var is NEMO_TOKEN (primaryEnv). That is proportionate for an API-backed render service. But the frontmatter also references a config path (~/.config/nemovideo/) which is not declared elsewhere; if the agent will read that directory to find stored credentials or state, that expands the scope of sensitive data accessed. Also the skill will obtain an anonymous token via an API if no token is present — that behavior is reasonable but should be known to the user.

Persistence & Privilege

The skill does not request always:true and does not claim to modify other skills or system-wide settings. It instructs saving a session_id and using tokens for subsequent calls, which is normal for a remote service integration.

What to consider before installing

This skill mostly does what it says (uploads audio and calls a remote render API using a NEMO_TOKEN), but there are two things to check before installing/using it: 1) clarify the config-path mismatch — SKILL.md frontmatter mentions ~/.config/nemovideo/ (which could contain credentials or state) though registry metadata lists no required config paths; ask the publisher whether the agent will read that directory and what it will do with any files found, 2) be aware the skill will accept a NEMO_TOKEN from your environment or obtain an anonymous token on your behalf (100 credits, 7-day expiry) and will upload files to mega-api-prod.nemovideo.ai — only upload audio you are comfortable sending to that service. If you need stronger assurance, request the skill source or an explicit privacy statement from the author, or decline until the config-path behavior is clarified.

Getting Started

Send me your audio files and I'll handle the audio to video conversion. Or just describe what you're after.

Try saying:

• "convert a 3-minute MP3 podcast recording into a 1080p MP4"
• "convert my audio file into a video with a waveform visualizer and background image"
• "uploading audio files to create shareable video content on AIOZ network for podcasters, musicians, 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.

Audio Upload AIOZ — Convert Audio Files to Video

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

A quick example: upload a 3-minute MP3 podcast recording, type "convert my audio file into a video with a waveform visualizer and background image", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.

Worth noting: shorter audio clips under 5 minutes process significantly faster on the AIOZ network.

Matching Input to Actions

User prompts referencing audio upload aioz, 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: audio-upload-aioz
• 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 Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s 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)

Common Workflows

Quick edit: Upload → "convert my audio file into a video with a waveform visualizer and background image" → 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 "convert my audio file into a video with a waveform visualizer and background image" — concrete instructions get better results.

Max file size is 200MB. Stick to MP3, WAV, AAC, M4A for the smoothest experience.

Export as MP4 for widest compatibility across social and streaming platforms.