Gemini 3.5 Transcribe

Google Gemini 3.5 speech-to-text for audio files up to one hour, with language detection, speaker diarization, word-level timestamps, and custom vocabulary.

Audio input: $1.80list $2.00-10%per 1M tokens

Context: 131K
Max output: 66K

30-day uptime: —

Released: 2026-08-26

InputAudioOutputText

Providers

Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.

AutoAudio input$1.80-10%Context131KMax output66KWe send each request to the best-priced healthy provider. You pay that provider’s price.Google (Gemini)Audio input$1.80-10%United StatesNo trainingNo retentionGoogle Vertex AIAudio input$1.80-10%GlobalNo training

Pricing

All prices for this model, by service tier.

Input: $1.80list $2.00-10%; per 1M tokens
Output: $10.80list $12.00-10%; per 1M tokens
Cache read: $1.80list $2.00-10%; per 1M tokens
Reasoning output: $10.80list $12.00-10%; per 1M tokens
Audio input: $1.80list $2.00-10%; per 1M tokens

Try it

Runs on your balance and is billed like any API request.

curl https://api.ohmygpt.com/v1/models/google/gemini-3.5-transcribe:generateContent \
  -H "x-goog-api-key: $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "Hello"
          }
        ]
      }
    ]
  }'

import os

from google import genai
from google.genai import types

client = genai.Client(
    api_key=os.environ["OHMYGPT_API_KEY"],
    http_options=types.HttpOptions(base_url="https://api.ohmygpt.com", api_version="v1"),
)

response = client.models.generate_content(
    model="google/gemini-3.5-transcribe",
    contents=[{"role": "user", "parts": [{"text": "Hello"}]}],
)
print(response.text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({
  apiKey: process.env.OHMYGPT_API_KEY,
  httpOptions: { baseUrl: "https://api.ohmygpt.com", apiVersion: "v1" },
});

const response = await client.models.generateContent({
  model: "google/gemini-3.5-transcribe",
  contents: [{ role: "user", parts: [{ text: "Hello" }] }],
});
console.log(response.text);

The answer streams in here.

Billed by usage

Similar models

Other models with the same output types at a similar price.

Gemini 3.5 TranscribeThis model

Audio input: $1.80per 1M tokens

Gemini 3.5 Transcribe Live

Audio input: $3.15per 1M tokens

GPT Live Transcribe

Transcription: $0.000256per second