Podcast To Video Maker

Get captioned video files ready to post, without touching a single slider. Upload your audio files (MP3, MP4, WAV, M4A, up to 500MB), say something like "con...

Security Scan

The skill's requests and runtime instructions largely match its stated purpose (converting uploaded audio into captioned video via a remote API), but there are a few minor inconsistencies and privacy considerations you should review before use.

Purpose & Capability

The skill describes converting podcast audio to video and its instructions call the nemo-video API endpoints for session creation, upload, SSE-driven editing, and export. Requiring a NEMO_TOKEN (or creating an anonymous token) is coherent with using a third‑party render API.

Instruction Scope

Instructions stay within the conversion workflow (auth, session creation, file upload, SSE editing, export). They do ask the agent to include attribution headers and to 'detect from install path' (e.g., ~/.clawhub/ or ~/.cursor/skills/) which implies the agent may inspect installation paths or environment to choose X-Skill-Platform — this is a minor scope creep compared to pure media processing and should be explicitly allowed by you.

Install Mechanism

This is an instruction-only skill with no install spec or code to write to disk, so there is no install-time download risk.

Credentials

The skill requires a single credential (NEMO_TOKEN) which is proportional to calling the remote API. The SKILL.md also documents an anonymous-token endpoint to obtain a short-lived token if NEMO_TOKEN is not set. One inconsistency: the registry metadata lists no required config paths, but the SKILL.md frontmatter mentions a config path (~/.config/nemovideo/). This mismatch should be clarified.

Persistence & Privilege

The skill does not request always:true or other elevated persistence. It does instruct saving session_id for job tracking (normal for a remote-job workflow).

Assessment

This skill appears to do what it says: it uploads audio to the nemo video service and returns rendered MP4s. Before installing: (1) Be aware audio files are sent to a third-party endpoint (mega-api-prod.nemovideo.ai) — avoid uploading sensitive content. (2) Prefer using the anonymous token flow for short-lived access rather than placing a long-lived NEMO_TOKEN in your environment. (3) Ask the skill author to clarify the configPaths discrepancy (SKILL.md frontmatter vs registry metadata) and to confirm exactly what filesystem checks (install-path detection) the agent will perform. (4) If you must provide a NEMO_TOKEN, ensure it has limited scope/permissions and can be revoked. (5) Test first with non-sensitive sample audio to verify behavior and outputs.

Getting Started

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

Try saying:

• "convert a 45-minute podcast episode in MP3 into a 1080p MP4"
• "convert my podcast into a video with captions and a waveform animation"
• "turning podcast audio into shareable videos for YouTube or social media for podcasters and 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.

Podcast to Video Maker — Convert Podcast Audio into Video

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

A quick example: upload a 45-minute podcast episode in MP3, type "convert my podcast into a video with captions and a waveform animation", and you'll get a 1080p MP4 back in roughly 1-3 minutes. All rendering happens server-side.

Worth noting: shorter clips under 10 minutes process significantly faster and work better for social clips.

Matching Input to Actions

User prompts referencing podcast to video maker, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: podcast-to-video-maker
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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.

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.

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

Tips and Tricks

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

Max file size is 500MB. Stick to MP3, MP4, WAV, M4A for the smoothest experience.

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

Common Workflows

Quick edit: Upload → "convert my podcast into a video with captions and a waveform animation" → Download MP4. Takes 1-3 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.