Gemini 3.5 Transcribe is Google's speech-to-text model, released 2026-09, built for synchronous transcription tasks that require precise timing and speaker separation. It supports word-level timestamps and speaker diarization for up to eight speakers, handling audio up to one hour long, or 30 minutes when those features are enabled.
Modalities
inAudiooutText
Price
$82.50/ 1M in
Context
98K
Released
Sep 25, 2026
Channels
Every channel serves the same model, but they differ in price and stability. On each API key in the Platform, you pick a primary and a backup channel per vendor, and each billing line shows which channel served the request.
Provider
Discount
Input /M
Cache read /M
Officialstable
+2846%
$82.50
—
Quick start
POST /v1/audio/transcriptionsimport os from openai import OpenAI client = OpenAI( base_url="https://api.mirapi.ai/v1", # changed api_key=os.environ["MIRAPI_API_KEY"], # changed ) resp = client.audio.transcriptions.create( model="gemini-3.5-transcribe", file=open("audio.mp3", "rb"), ) # resp.text
import fs from "node:fs"; import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.mirapi.ai/v1", // changed apiKey: process.env.MIRAPI_API_KEY, // changed }); const resp = await client.audio.transcriptions.create({ model: "gemini-3.5-transcribe", file: fs.createReadStream("audio.mp3"), });
curl https://api.mirapi.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $MIRAPI_API_KEY" \ -F "model=gemini-3.5-transcribe" \ -F "file=@audio.mp3"
Links
Wire Gemini 3.5 Transcribe into your product
Start free1M free tokens to start, no card required. It’s OpenAI-compatible, so you only change the base URL.