Audioelevenlabselevenlabs-speech-to-text-scribe-v2
ElevenLabs Scribe v2 (STT)
Speech-to-text transcription via ElevenLabs Scribe v2. Word-level timestamps, speaker diarization, language auto-detect. Optional keyterm boosting (+30% cost when used).
Parameters
- audio_urlstringMP3 / OGG / WAV / M4A / AAC. Drag-and-drop or URL.
- keytermsarrayBoost recognition of specific terms. +30% cost when used.