Google: Gemini 3.5 Transcribe Live
Google Gemini 3.5 Transcribe Live API pricing
Gemini 3.5 Transcribe Live costs $1.40 per million input tokens and $8.40 per million output tokens on Oxyy. These are the pay-as-you-go prices after the current 60% discount (Launch Promo; standard price $3.50 input and $21.00 output). It takes audio as input and returns text, from audio files of up to 50 MB. A cheaper Google option is Gemini 3.5 Transcribe at $0.800 / $4.80 per 1M tokens; for every model and rate, see Gemini API pricing.
Providers
Where this model runs, and what each route costs. Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.
| Provider | Input /M | Output /M | Cache read /M |
|---|---|---|---|
| $1.40 | $8.40 | — |
Capabilities (11)
Supported parameters (6)
The endpoint's own fields, shown in the quickstart below, are required as well; a request without them is rejected.
Pricing
What this model costs on Oxyy, pay as you go. "Charged" is the rate a request is billed at; the standard price is shown beside it for reference.
| Rate | Standard price | Charged | Unit |
|---|---|---|---|
| Input | $3.50 | $1.40 | per 1M input tokens |
| Output | $21.00 | $8.40 | per 1M output tokens |
Discount. Charged rates include the current "Launch Promo" discount of 60% on every rate.
Specifications
- Model ID
gemini-3.5-transcribe-live- Developer
- Type
- Speech to text
- Input
- Audio
- Output
- Text
- Context window
- 96,000 tokens
- Released
- Aug 26, 2026
- Audio input
- Up to 50 MB each
- Endpoint
/v1/audio/transcriptions
Quickstart
Call gemini-3.5-transcribe-live with a POST to /v1/audio/transcriptions on https://api.oxyy.ai, using your Oxyy API key from the OXYY_API_KEY environment variable. The same key works for every model in the catalog.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.oxyy.ai/v1",
api_key=os.environ["OXYY_API_KEY"],
)
with open("interview.mp3", "rb") as audio_file:
response = client.audio.transcriptions.create(
model="gemini-3.5-transcribe-live",
file=audio_file,
)
print(response.text)Availability
The share of requests to this model that completed successfully over the last 30 days. Requests the caller cancelled, and requests still in flight, are not counted. When an upstream provider errors, the gateway retries against another provider serving the same model, so a single provider incident does not necessarily show up here.
Frequently asked questions
What is Gemini 3.5 Transcribe Live?
How much does Gemini 3.5 Transcribe Live cost?
What audio files can Gemini 3.5 Transcribe Live transcribe?
How do I call Gemini 3.5 Transcribe Live through the API?
When was Gemini 3.5 Transcribe Live released?
What other models does Google have?
Alternatives to Gemini 3.5 Transcribe Live
Models of the same kind from other vendors, closest in price first. Prices are pay-as-you-go on Oxyy, through the same API key.