Remy Reference/Models/Transcription/Whisper-1

Whisper-1

Whisper-1, a transcription model from OpenAI.

transcriptionModelOverride: { model: "whisper-1" }

OOpenAI·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.

Parameter	Type	Default	Range / options
`includeWordTimings` Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.	Select	no	yesno

Use this model

await mindstudio.transcribeAudio({
  audioUrl: "...",
  transcriptionModelOverride: {
    model: "whisper-1",
    config: {
      includeWordTimings: "no",
    },
  },
});