Yt Assemblyai Monitor

YouTube channel monitor and video transcription using AssemblyAI cloud API. Pure Python + requests only — no ffmpeg, no Whisper, no extra tools needed. Monit...

Security Scan

The skill mostly does what it says (monitor YouTube + transcribe via AssemblyAI) but the package metadata omits the required AssemblyAI credential, the shipped code includes a hard-coded innertube API key fallback, and the distributed source is truncated so a full audit isn't possible — these inconsistencies and unknowns warrant caution.

Purpose & Capability

The skill's stated purpose is YouTube monitoring + AssemblyAI transcription, which matches the code's behavior. However, the registry metadata declares no required environment variables or primary credential, while the SKILL.md and monitor.py require an ASSEMBLYAI_API_KEY (or data/config.json). That mismatch is incoherent and should have been declared in the skill metadata.

Instruction Scope

Instructions and code confine activity to fetching YouTube pages, extracting audio URLs via the innertube API, and submitting those URLs to AssemblyAI. The skill reads/writes files inside its own data/ directory (channels.json, processed.json, summaries, config.json). It does not attempt to read other system files or unrelated environment variables. It does, however, offer storing the API key in plaintext at data/config.json which raises disclosure risk if the host environment is shared.

Install Mechanism

There is no install spec — the skill is instruction/code-only and uses only the requests library. Nothing is downloaded or executed from external, arbitrary URLs during install.

Credentials

The skill requires an AssemblyAI API key to function (documented in SKILL.md and enforced in code) but the registry metadata does not declare this required credential. Requesting an API key for the service being used is reasonable, but storing it in a local plaintext config file is risky. Additionally, the code contains a hard-coded INNERTUBE_API_KEY fallback (a Google API key string) — using or exposing a fallback API key is unusual and may be inappropriate.

Persistence & Privilege

The skill is not always-enabled and does not request special platform privileges. It writes only to its own data/ directory and does not modify other skills or system-wide settings.

What to consider before installing

This skill appears to perform the advertised YouTube→AssemblyAI workflow, but there are two issues to consider before installing: (1) the registry metadata does NOT list the AssemblyAI API key requirement despite the SKILL.md and code requiring ASSEMBLYAI_API_KEY — provide the key only if you trust and understand the billing/usage implications; (2) the code includes a hard-coded innertube API key fallback (a Google API key string) and suggests storing your AssemblyAI key in data/config.json (plaintext) — prefer using the ASSEMBLYAI_API_KEY environment variable rather than a config file to reduce accidental exposure. Also note the provided scripts/monitor.py in the package snapshot is truncated, so the audit is incomplete; you should inspect the full source before running. Recommended actions: review the full monitor.py, run the script in a sandbox or isolated environment, avoid committing config.json to version control, and monitor your AssemblyAI account for unexpected usage after enabling the skill.

YouTube Channel Monitor (AssemblyAI)

Monitor YouTube channels and auto-transcribe new videos using AssemblyAI cloud API. Zero local dependencies beyond requests.

Prerequisites

1. AssemblyAI account: https://www.assemblyai.com/app/signup (free, 100 hours/month)
2. API Key: from Dashboard
3. requests library (usually pre-installed with OpenClaw/Python)

Setup API Key

Choose one:

# Option A: environment variable
export ASSEMBLYAI_API_KEY="your-key"

# Option B: config file
echo '{"api_key": "your-key"}' > data/config.json

How It Works

Channel page → innertube API → audio direct URL → AssemblyAI cloud → text + summary

No local audio download, no Whisper, no ffmpeg. AssemblyAI handles everything server-side.

Commands

# Transcribe a single video
python3 scripts/monitor.py now "https://www.youtube.com/watch?v=VIDEO_ID"

# Add a channel to monitor
python3 scripts/monitor.py add "https://www.youtube.com/@ChannelName/videos" "Alias"

# Check all channels for new videos + transcribe
python3 scripts/monitor.py check [count_per_channel]

# List channels
python3 scripts/monitor.py list

# Remove channel
python3 scripts/monitor.py remove "Alias"

Important Notes

• Audio URL extraction uses YouTube's innertube API (pure requests).
• Works on normal residential IPs. Datacenter IPs may get blocked by YouTube.
• If audio URL extraction fails with UNPLAYABLE, the IP may be flagged — this is a YouTube limitation, not a bug.
• Free tier: 100 hours/month of transcription.
• Transcription takes ~70-80% of video duration.
• Results saved to data/summaries/{video_id}.json.

Output Format

Each result includes:

• text: full transcription
• summary: AI-generated paragraph summary
• confidence: transcription confidence score
• utterances: timestamped segments with speaker labels

Files

Path	Purpose
data/channels.json	monitored channels
data/processed.json	already-transcribed video IDs
data/summaries/*.json	transcription results
data/config.json	API key (optional)