ElevenLabs Speech-to-Text
Transcribe audio files using ElevenLabs' Scribe v2 model with support for 90+ languages, speaker diarization, audio event detection, and word-level timestamps.
🚀 Transcribe audio files into text with ElevenLabs Speech-to-Text. Supports 90+ languages with automatic detection, speaker identification, and audio event tagging (laughter, music, applause). Get precise word-level timestamps and process all major audio formats—mp3, wav, m4a, ogg, webm, and more.
💡 Perfect for meetings, podcasts, voice notes, and interviews. Identify who's speaking, extract exact timing for editing, and process multilingual content effortlessly. Ideal for journalists, researchers, content creators, and teams needing accurate transcriptions fast.
✨ Built-in speaker diarization distinguishes multiple voices automatically. JSON output with timestamps enables seamless integration into workflows, while automatic language detection removes setup friction.
Requirements
ElevenLabs API key with Speech-to-Text access
Command-line tool for making API requests
JSON query processor for parsing responses (optional but recommended)