podcast-video-cameraGet polished podcast videos ready to post, without touching a single slider. Upload your raw footage (MP4, MOV, AVI, WebM, up to 500MB), say something like "...
Install via ClawdBot CLI:
clawdbot install peand-rover/podcast-video-cameraGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token`Calls external URL not in known-safe list
https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token`AI Analysis
The skill sends user data (uploaded video files) to an external API for processing, which is consistent with its stated purpose of AI video editing. However, the external endpoint is not documented in a known-safe list, and the authentication mechanism involves generating and sending a UUID to obtain a token, which is a standard pattern for anonymous access but introduces a dependency on an unvetted third-party service.
Audited Apr 16, 2026 · audit v1.0
Generated May 9, 2026
A podcast creator uploads a 60-minute raw recording with two hosts, requests removal of filler words and addition of captions, and downloads a polished 1080p MP4 in 1-2 minutes. This saves hours of manual editing.
A content creator takes a long podcast recording, splits it into segments, and exports short clips with text overlays for platforms like Instagram or TikTok. The skill handles aspect ratio and compression automatically.
A journalist uploads a multi-camera interview recording, asks for filler word removal and clean audio, and exports a final version with synchronized video. The pipeline handles uploads up to 500MB.
An educator records a lecture-style podcast, uses the skill to add captions for accessibility, and exports a 1080p video for distribution on learning platforms. The 15-minute SSE timeout supports lengthy edits.
A team lead uploads a weekly update recording, requests removal of mistakes and addition of branding overlays, and exports a polished video for internal distribution. The free credits allow testing with minimal investment.
New users get 100 free credits valid for 7 days via anonymous token generation. Once exhausted, users must register and purchase credits, with costs based on render duration or exports.
Users can subscribe to monthly plans offering a set number of exports or unlimited processing. Higher tiers provide priority GPU access, larger file size limits, and custom branding options.
Users pay a fixed fee per completed export without a subscription. This appeals to occasional podcasters who prefer not to commit to a monthly plan.
💬 Integration Tip
To integrate, set the NEMO_TOKEN environment variable and ensure config directory ~/.config/nemovideo/ is writable. Use the provided API endpoints with required headers to automate the pipeline.
Scored May 9, 2026
Local speech-to-text with the Whisper CLI (no API key).
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...