Blazingly fast speech-to-text with speaker diarization, audio event tagging, and word-level timestamps. Scribe V2 from ElevenLabs with multilingual support
Fill in the parameters below and click "Generate" to try this model
Audio file to transcribe
Language code of audio (ISO 639-3)
Tag audio events (laughter, applause, etc.)
Annotate who is speaking (speaker diarization)
Bias model towards specific words (max 100, 50 chars each, +30% cost)
Your inputs will be saved and ready after sign in
Analyze audio files to identify topics, emotions, speakers, and extract insights.
Hey! Need help? 👋
Click to chat with us