---
id: "google/gemini-3.5-transcribe"
also: ["google/gemini-3.5-transcribe-20260827", "vercel/google/gemini-3.5-transcribe"]
cheapest_list_usd_per_m: "2.0 in, 12.0 out, at google-ai-studio on openrouter"
cheapest_effective_usd_per_m: "2.0 in, 12.0 out, at google-ai-studio on openrouter"
context: 98304
max_output: 32768
input: ["audio"]
output: ["transcription"]
released: "2026-09-25"
api: ["/api/v1/audio/transcriptions"]
params: ["include_reasoning", "max_tokens", "reasoning", "stop", "temperature"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 1
trains: 0
retains_prompts: 1
---
# Google: Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio...