opendunes

Gemini 3.5 Transcribe

by GoogleReleased 25 September 2026

Gemini 3.5 Transcribe turns audio files into text, detecting the language among 85+ and optionally adding the time of each word, speaker labels for as many as eight speakers, and filler-word removal. A request runs up to an hour, or 30 minutes with speakers or timestamps.

TakesAudio
GivesText

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Google AI Studio…
↑ Sent, per 1M
665,67 DA
↓ Back, per 1M
3 994,03 DA
Latency
…
Provider↑ Sent↓ BackLatencyUptime
Google AI Studio665,67 DA3 994,03 DA……

You pay the price of the provider that served your request. Prices read 02:48 · speed over the last 30 minutes · uptime over 3 days.

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 1,80 DA per minute of audio3 000 DA buys about 1 600 minutes of audio

One minute of audio, the ordinary use

1 500 sent1 500 audio tokens sent× 665,67 per 1M× 665,67 DA per 1M1,00 DA
200 back200 tokens back× 3 994,03 per 1M× 3 994,03 DA per 1M0,80 DA
Total≈ 1,80 DA

Every rate

Meter↑ you send↓ comes back
Text tokens665,67 DA3 994,03 DA

per 1M tokens

Everyday jobs, priced

Transcribe a 2-minute voice note≈ 3,39 DA
Transcribe a 10-minute customer call with speaker labels≈ 16,97 DA
Transcribe a 30-minute team meeting≈ 50,92 DA
Transcribe a 45-minute lecture≈ 76,39 DA
Transcribe a one-hour podcast episode≈ 101,85 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the audio.
After each one
The exact charge shows on the request.
Add creditDeposits from 100 DA, withEdahabiaCIB

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/audio/transcriptions
Base URL
https://opendunes.com/v1
Model ID
google/gemini-3.5-transcribe
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

with open("meeting.mp3", "rb") as f:
    resp = client.audio.transcriptions.create(model="google/gemini-3.5-transcribe", file=f)

print(resp.text)

Runs this request once on your balance.

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window
98 304 tokens
Max output
32 768 tokens
Reads at once
not stated
Longest reply
≈ 25 000 words
Tokenizer
Gemini
Released
25 Sep 2026
Full API reference

Questions about Gemini 3.5 Transcribe

How much does Gemini 3.5 Transcribe cost in dinars?

About 1,80 DA per minute of audio. ↑ 665,67 DA · ↓ 3 994,03 DA per 1M tokens.

Is Gemini 3.5 Transcribe free? Can I try it?

No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.

What is Gemini 3.5 Transcribe best for?

Gemini 3.5 Transcribe turns audio files into text, detecting the language among 85+ and optionally adding the time of each word, speaker labels for as many as eight speakers, and filler-word removal. A request runs up to an hour, or 30 minutes with speakers or timestamps.

How do I pay for Gemini 3.5 Transcribe without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Gemini 3.5 Transcribe included, is paid from that balance. No foreign card, no conversion.

Does Gemini 3.5 Transcribe work in Arabic, French or Darja?

Google says it detects more than 85 languages and handles speakers who switch language. The page does not name Arabic, French or Darja.

Does it say who spoke, and when?

Speaker labels: yes. Word timings: yes.

How long can a file be?

Up to 25 MB as an upload. Longer audio goes in the request body.

Who makes Gemini 3.5 Transcribe, and when was it released?

Google. Released 25 September 2026.

Other Google models, priced in dinars

See all Google models
Gemini Omni 1.2 FlashGoogle · Nov 5, 2026

This model is designed to handle text, pictures, and video inputs, allowing it to read up to 130 pages of content. It specializes in generating and editing video clips, producing outputs that include both text and moving images. What sets this model apart is its native ability to process and generate video content directly. It is not suitable for tasks requiring external tool usage or the creation of structured data formats.

Searches the webThinks first130 pages at once
≈2,00 DAper message
View model
Gemini 3.8 Flash TTSGoogle · Sep 23, 2026

#1 for speech · Gemini 3.8 Flash TTS turns text into speech in 130+ languages with studio-grade acting, regional accents and a voice that stays consistent through long dialogues. It offers prebuilt voices, custom voice personas and voice replication, with about 8 pages of text per request. Pick it for audiobooks, narration and multi-speaker scenes.

30 voices
≈3,02 DAper paragraph read aloud
View model
Gemini Omni 1.1 FlashGoogle · Nov 4, 2026

This model accepts text, pictures, and videos as input, allowing it to read up to 130 pages of content. It specializes in creating and editing video content, converting descriptions or pictures into moving images. A key feature is its ability to search the web for information while processing complex visual data. However, it does not utilize external tools or generate structured data formats.

Searches the webThinks first130 pages at once
≈2,00 DAper message
View model
Gemini 3.8 Flash Lite TTSGoogle · Sep 23, 2026

Flash Lite TTS from the 3.8 family turns text into speech in 101 languages, built for large volumes of audio, live voice assistants and read-aloud features. It offers prebuilt voices, custom voice personas and voice replication, with about 8 pages of text per request. Pick it for speed and volume.

30 voices
≈2,02 DAper paragraph read aloud
View model