opendunes

Chirp 3

by GoogleReleased 5 May 2026

Chirp 3 is the speech-to-text model from Google: send audio, get a transcript with punctuation added and the language detected for you. It covers 50+ languages and handles clips under a minute and recordings up to an hour, and it can tell speakers apart when you process recordings in batches. Pick it for multilingual call or meeting audio.

TakesAudio
GivesText
Open in chatCreate API keyCompare

What it costs

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

5,33 DA per minute of audio3 000 DA buys 560 minutes of audio

One minute of audio, the ordinary use

60 seconds of audio sent× 0,089 DA5,33 DA
Total5,33 DA

Every rate

Meter↑ you send↓ comes back
Second of audio0,089 DA

per second of audio sent

Transcribe a 1-minute voice note≈ 5,33 DA
Transcribe a 5-minute customer call≈ 26,63 DA
Transcribe a 20-minute interview≈ 106,51 DA
Transcribe a 30-minute meeting≈ 159,76 DA
Transcribe a one-hour training video≈ 319,52 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.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it.

Google…
Per second of audio
0,089 DA
Latency
…
ProviderPer second of audioLatencyUptime
Google0,089 DA……

You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.

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/chirp-3
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/chirp-3", file=f)

print(resp.text)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Questions about Chirp 3

  • How much does Chirp 3 cost in dinars?

    About 5,33 DA per minute of audio. ↑ 0,089 DA per second of audio.

  • Is Chirp 3 free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Chirp 3 best for?

    Chirp 3 is the speech-to-text model from Google: send audio, get a transcript with punctuation added and the language detected for you. It covers 50+ languages and handles clips under a minute and recordings up to an hour, and it can tell speakers apart when you process recordings in batches. Pick it for multilingual call or meeting audio.

  • How do I pay for Chirp 3 without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Chirp 3 included, is paid from that balance. No foreign card, no conversion.

  • Does Chirp 3 work in Arabic, French or Darja?

    Google lists French (France and Canada) as generally available and many Arabic variants in preview, Arabic (Algeria) among them. Darja is not named as such.

  • Does it say who spoke, and when?

    Speaker labels: not stated. Word timings: not stated.

  • How long can a file be?

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

  • Who makes Chirp 3, and when was it released?

    Google. Released 5 May 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
Nano Banana 2 (Gemini 3.1 Flash Image)Google · Jun 18, 2026

Nano Banana 2, Google's 3.1 Flash Image model, generates and edits images from a written description and reference pictures, returning images with text. It outputs up to 4K, adds very tall and very wide shapes such as 1:8, and renders text in other languages better. Pick it for production batches of ads, banners and edits.

Up to 14 references4K
≈24,60 DAper image
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