ElevenLabs Audio Transcription

1. Enter your ElevenLabs API Key

2. Enter Audio URL

3. Select Transcription Model

4. Advanced Parameters

Language Code (optional): ISO-639-1 or ISO-639-3 code. If omitted, language is auto-detected.

Enable Logging: Set to false for zero retention mode (enterprise only).

Tag Audio Events: Set to false to omit tags like (laughter), (footsteps), etc.

Number of Speakers: Integer between 1 and 32. Helps in speaker diarization.

Timestamps Granularity: Choose between word or character for timestamp precision.

Enable Speaker Diarization: Set to true to enable speaker diarization.

Processing...

Transcription Results