Podcast Video Online

convert audio or video files into shareable podcast videos with this skill. Works with MP3, MP4, WAV, MOV files up to 500MB. podcasters and content creators...

Security Scan

The skill mostly does what it claims (convert uploaded audio/video via a remote API) but has small but meaningful inconsistencies around credentials and metadata that you should understand before installing.

Purpose & Capability

The declared purpose (convert podcast audio/video to shareable MP4) matches the API endpoints and operations described in SKILL.md. However the registry metadata vs the skill frontmatter disagree: the registry reported no required config paths while the SKILL.md metadata embeds configPaths (~/.config/nemovideo/). Also the skill declares NEMO_TOKEN as a required/primary credential but its runtime instructions include an anonymous-token flow that obtains a token automatically — making the declared "required" env var inconsistent with the runtime behavior.

Instruction Scope

Runtime instructions are limited to interactions with the nemovideo.ai API (auth, session creation, upload, render, poll, download). The skill instructs generating a client UUID and posting to an anonymous-token endpoint if no NEMO_TOKEN is present. It asks to detect install path for an X-Skill-Platform header (minor local path inspection) but does not instruct reading unrelated files or other environment variables.

Install Mechanism

No install spec or code is present (instruction-only). That minimizes disk-write and arbitrary code risk.

Credentials

Only NEMO_TOKEN is declared, which is appropriate for an API-backed service. But the SKILL.md provides automatic anonymous-token acquisition if NEMO_TOKEN is absent, so requiring NEMO_TOKEN seems unnecessary or inconsistent. The skill will perform network requests to obtain/use tokens and store a session_id; how and where tokens/session IDs are stored is not specified.

Persistence & Privilege

always:false and no instructions to modify other skills or system-wide config. The skill asks the agent to store a session_id for subsequent requests — normal for a session-based API — but does not request permanent elevated presence.

What to consider before installing

This skill calls a third‑party API (mega-api-prod.nemovideo.ai) to upload your files and render videos. Before installing: 1) Note the skill can auto-request an anonymous token from that service if you don't supply NEMO_TOKEN — it will make outbound network calls and create a session token valid for a limited time. 2) Clarify where tokens/session IDs are stored (are they persisted to disk or agent config?), and whether uploads or generated videos are retained by the provider or shared. 3) Be cautious about uploading sensitive content (private conversations, copyrighted material) because files are sent to the provider. 4) The registry metadata and SKILL.md disagree about config paths and credential requirements — ask the skill author or maintainer to resolve the inconsistency before trusting persistent installation. If you trust the nemovideo.ai service and are comfortable with remote processing, the skill appears coherent; if you need guarantees about data retention or token storage, request more detail or avoid installing.

Getting Started

Send me your audio or video files and I'll handle the AI podcast video creation. Or just describe what you're after.

Try saying:

• "convert a 30-minute podcast audio recording in MP3 into a 1080p MP4"
• "turn my podcast audio into a video with captions and a waveform visual"
• "converting podcast audio into captioned videos for YouTube or social media for podcasters and content creators"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Podcast Video Online — Convert Podcast Audio to Video

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

A quick example: upload a 30-minute podcast audio recording in MP3, type "turn my podcast audio into a video with captions and a waveform visual", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: splitting long episodes into shorter clips increases engagement on social platforms.

Matching Input to Actions

User prompts referencing podcast video online, 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: podcast-video-online
• 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

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)

Common Workflows

Quick edit: Upload → "turn my podcast audio into a video with captions and a waveform visual" → 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "turn my podcast audio into a video with captions and a waveform visual" — concrete instructions get better results.

Max file size is 500MB. Stick to MP3, MP4, WAV, MOV for the smoothest experience.

Export as MP4 for widest compatibility across YouTube, Spotify, and social media.