opendunes

Grok STT 2.0

New

by xAIReleased 10 November 2026

This speech-to-text model takes a recording of spoken words and hands back a written transcript. It marks the exact time of every word and, when asked, notes who said what, which suits turning meetings, interviews or podcasts into readable text. It is the newer edition in this family of transcription models, built as the successor to the one before it. It only turns speech into text; it cannot compose new writing or answer questions, so jobs that need generated text call for a different kind of model.

TakesAudio
GivesText

Where your request runs

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

xAI…
Per second of audio
0,0092 DA
Latency
…
ProviderPer second of audioLatencyUptime
xAI0,0092 DA……

You pay the price of the provider that served your request. Prices read 02:47 · speed over the last 30 minutes · uptime over 3 days.

What it costs

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

0,55 DA per minute of audio3 000 DA buys 5 400 minutes of audio

One minute of audio, the ordinary use

60 sent60 seconds of audio sent× 0,0092× 0,0092 DA0,55 DA
Total0,55 DA

Every rate

Meter↑ you send↓ comes back
Second of audio0,0092 DA

per second of audio sent

Everyday jobs, priced

Transcribing a two-minute voicemail1,11 DA
Getting a written record of a 30-minute interview16,64 DA
Transcribing a one-hour recorded meeting33,28 DA
Captioning a one-hour podcast episode33,28 DA
Making lecture notes from a 90-minute class recording49,92 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
x-ai/grok-stt-2.0
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="x-ai/grok-stt-2.0", 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
not stated
Max output
not stated
Reads at once
not stated
Longest reply
not stated
Tokenizer
Grok
Released
10 Nov 2026
Full API reference

Questions about Grok STT 2.0

How much does Grok STT 2.0 cost in dinars?

About 0,55 DA per minute of audio. ↑ 0,0092 DA per second of audio.

Is Grok STT 2.0 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 Grok STT 2.0 best for?

This speech-to-text model takes a recording of spoken words and hands back a written transcript. It marks the exact time of every word and, when asked, notes who said what, which suits turning meetings, interviews or podcasts into readable text. It is the newer edition in this family of transcription models, built as the successor to the one before it. It only turns speech into text; it cannot compose new writing or answer questions, so jobs that need generated text call for a different kind of model.

How do I pay for Grok STT 2.0 without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Grok STT 2.0 included, is paid from that balance. No foreign card, no conversion.

Does Grok STT 2.0 work in Arabic, French or Darja?

xAI names no languages for Grok STT 2.0. Arabic, French and Darja: not stated.

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 Grok STT 2.0, and when was it released?

xAI. Released 10 November 2026.

Other xAI models, priced in dinars

See all xAI models
Grok Voice TTS 1.0xAI · May 15, 2026

Grok Voice TTS 1.0 reads text aloud in 20 or more languages and detects the language by itself. Its built-in voices are named Eve, Ara, Rex, Sal and Leo, and short tags in the text set speed, pitch, pauses, emphasis and style. You get a sound file such as MP3 or WAV, with at most 15,000 characters at a time. It only speaks; Grok STT 1.0 does the reverse and writes speech down.

5 voices
≈3,00 DAper paragraph read aloud
View model
Grok Imagine Image 2.0xAI · Aug 11, 2026

Grok Imagine Image 2.0 takes a written description, and optionally pictures to work from, and returns a new or edited image. It offers two quality settings, low and medium. Pick it for everyday image making and edits from reference pictures.

Up to 5 references
19,97 DAper image
View model
Grok Imagine Video 1.5xAI · Jul 20, 2026

Grok Imagine Video 1.5 makes a video from a written description, with an optional starting picture to set the scene. You can direct how the subject and camera move, the pacing and the mood, and it can add matching sound effects, background sound and spoken lines. Pick it for the best quality of the three. Grok Imagine Video 1.5 Lite is quicker, and Grok Imagine Video takes up to seven reference pictures.

Makes soundAnimates your photoUp to 15 s
26,63 DAper second of video
View model
Grok Imagine Video 1.5 LitexAI · Oct 6, 2026

Grok Imagine Video 1.5 Lite makes a video from a written description or from a starting picture. It is a faster, lighter version of the regular model, giving up a little quality for speed, and a Full HD request is rendered in HD and enlarged. Pick it for quick drafts and tests.

Makes soundAnimates your photoUp to 15 s
6,66 DAper second of video
View model