Transcribe Audio
transcribe_audioSpeech-to-text + optional speaker diarization (ElevenLabs Scribe). Returns { languageCode, durationSec, text, speakers, segments } where segments are contiguous same-speaker runs with start/end seconds — use them to pick clean windows (e.g. for clip_audio → clone_voice). Scope required: transcribe:audio.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| diarize | No | ||
| audioUrl | Yes | ||
| languageCode | No |