Eachlabs TTS
A Clawdbot skill for transcribing audio from URLs using EachLabs' ElevenLabs Scribe v1 model integration. Supports 32+ languages, speaker diarization, audio event tagging, and word-level timestamps.
🚀 Transcribe audio from URLs into text with EachLabs' ElevenLabs Scribe. Supports 32+ languages, speaker identification, and precise word-level timestamps. Perfect for converting podcasts, meetings, voice notes, and recordings into searchable, editable text.
💡 Ideal for content creators, researchers, and teams who need accurate transcriptions with speaker labels and audio event detection (laughter, music, applause). Extract insights from audio without manual listening.
✨ Get detailed JSON output with timestamps, automatic language detection, and optional speaker diarization—all from a simple URL input.
Requirements
API key from EachLabs for accessing ElevenLabs Scribe v1 model
Command-line tool for making HTTP requests
JSON query processor for parsing API responses