Remy Reference/models/Gemini 3.5 Transcribe

Gemini 3.5 Transcribe

Gemini 3.5 Transcribe, a transcription model from Google.

transcriptionModelOverride: { model: "gemini-3.5-transcribe" }

GGoogle·Released August 2026

Pricing

List price: ~$0.005 / min
Input: $2.00 / 1M
Output: $12.00 / 1M

Specifications

Released: August 2026
Model string: gemini-3.5-transcribe-preview
Capabilities: MultilingualLow cost

Parameters

Model options, passed in transcriptionModelOverride.config.

Parameter	Type	Default	Range / options
`includeSpeakers` Label each utterance with its speaker. Recordings up to 30 minutes, and not with key terms.	Select	no	yesno
`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	—	—
`includeWordTimings` Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.	Select	no	yesno
`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: "gemini-3.5-transcribe",
    config: {
      includeSpeakers: "no",
      includeWordTimings: "no",
    },
  },
});