ReferenceAsk
E

Scribe v3

Scribe v3, a transcription model from ElevenLabs.
transcriptionModelOverride: { model: "elevenlabs-scribe-v3" }
ElevenLabs·Released November 2026
Pricing
List price
$0.20 / hour
Per second
$0.000056
Per minute
$0.0033
Per second
$0.000014
Per minute
$0.00083
Per second
$0.000033
Per minute
$0.0020
Specifications
Released
November 2026
Model string
scribe_v3
Capabilities
Multilingual
Parameters
Model options, passed in transcriptionModelOverride.config.
ParameterTypeDefaultRange / options
includeSpeakers
Choose whether to include timing and speaker information in the transcription
Selectnoyesno
numSpeakers
The most people talking in the audio, when you know it. Helps the model tell speakers apart.
Number—1–32, step 1
language
The spoken language, as a code such as en or es. Leave as Auto to have the model detect it.
Select—enesfrdeitpt+7
keyterms
Names, products and terms the audio contains, so the model spells them right.
Text list——
redactPii
Replace names, phone numbers, addresses and other personal information in the transcript with a label of what was there.
Selectnoyesno
includeWordTimings
Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.
Selectnoyesno
subtitles
Also return the transcript as a subtitle file, SRT or WebVTT, timed to the audio.
Select—srtvtt
Use this model
await mindstudio.transcribeAudio({
  audioUrl: "...",
  transcriptionModelOverride: {
    model: "elevenlabs-scribe-v3",
    config: {
      includeSpeakers: "no",
      redactPii: "no",
    },
  },
});