ReferenceAsk
Back to Remy
Remy Reference/models/Whisper-1
O

Whisper-1

Whisper-1, a transcription model from OpenAI.
transcriptionModelOverride: { model: "whisper-1" }
OpenAI·Released September 2022
Pricing
List price
$0.006 / minute
Per second
$0.00010
Per minute
$0.0060
Per second
$0
Per minute
$0
Specifications
Released
September 2022
Capabilities
Open sourceLow cost
Parameters
Model options, passed in transcriptionModelOverride.config.
ParameterTypeDefaultRange / options
language
The spoken language, as a code such as en or es. Leave as Auto to have the model detect it.
Select—enesfrdeitpt+7
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: "whisper-1",
    config: {
      includeWordTimings: "no",
    },
  },
});