hide.st

ElevenLabs Scribe v3

elevenlabs/scribe-v3

ElevenLabs Scribe v3 transcribes recorded speech with automatic language detection, word timestamps, optional speaker labels, and audio event tagging. Choose digits or words for numbers, add secondary language hints, or provide up to 100 keyterms. Supports MP3, WAV, OGG, M4A, and AAC recordings up to 60 minutes, with direct uploads up to 4 MB or audio URLs up to 25 MB. Pricing is $0.01 per input minute, or $0.012 with keyterms, with a 10-second minimum and proportional billing thereafter.

  • Speech to text

Pricing

Includes our margin. Charged per request from your balance.

Per minute
$0.011
With keyterms per minute
$0.013
Rounding
Proportional
Maximum billable seconds
3600 s
Minimum billable seconds
10 s

Details

Provider
ElevenLabs
Added
Nov 22, 2026

Options

Parameters this model accepts.

Features
Automatic language detection, Word-level timestamps, Speaker diarization, Audio event tagging, Number formatting, Secondary language hints, Keyterms (20% surcharge)
Response formats
  • json
  • text
  • verbose_json
Input formats
MP3, WAV, OGG, M4A, AAC
Max file size
25 MB
Max upload in the request
4 MB
File URLs
Supported
Timestamps
  • word

Search

Search pages, chats and models