AssemblyAI Transcriber
PassAudited by ClawScan on May 1, 2026.
Overview
This skill appears to do what it claims: it sends user-selected audio to AssemblyAI for transcription using an AssemblyAI API key.
Before installing, make sure you are comfortable sending selected audio files or URLs to AssemblyAI and using your AssemblyAI API key for any resulting account usage or costs.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Private meeting, interview, podcast, or voice-message audio may be sent to AssemblyAI for processing.
The script uploads the selected local audio file to AssemblyAI over its API, which is central to the transcription purpose but means audio content leaves the local environment.
BASE_URL = "https://api.assemblyai.com/v2" ... with open(file_path, "rb") as f: file_data = f.read() ... f"{BASE_URL}/upload"Only transcribe files you are comfortable sending to AssemblyAI, and review AssemblyAI's privacy, retention, and billing terms for sensitive recordings.
Transcriptions and usage charges are tied to the AssemblyAI account whose key is available to the skill.
The skill uses an AssemblyAI account API key from environment or local config files to authorize transcription and upload requests.
CONFIG_PATHS = [Path.home() / ".assemblyai_config.json", Path.cwd() / ".assemblyai_config.json", ...] ... return config.get("api_key") ... "Authorization": api_keyStore the API key deliberately, protect config file permissions, remove stale workspace config files, and monitor AssemblyAI usage.