opendunes

Speech 2.8 Turbo

by MiniMaxReleased 16 July 2026

MiniMax Speech 2.8 Turbo turns text into speech and returns audio, using any MiniMax voice you name, with the same abilities as the HD version: emotion settings and tags for laughs and sighs written into the text. It is tuned for speed, so it fits assistants and apps that speak replies as they are produced.

TakesText
GivesAudio
Open in chatCreate API keyCompare

What it costs

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

≈ 11,98 DA per paragraph read aloud3 000 DA buys about 250 paragraphs read aloud

One paragraph read aloud, the ordinary use

600 characters sent× 19 970,14 DA per 1M11,98 DA
Total≈ 11,98 DA

Every rate

Meter↑ you send↓ comes back
Characters19 970,14 DA

per 1M characters

Record a phone menu greeting≈ 3,99 DA
Voice a 30-second product ad≈ 8,99 DA
Read a 600-character paragraph aloud≈ 11,98 DA
Narrate a short story for children≈ 29,96 DA
Read a one-page article aloud≈ 59,91 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the text.
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. DA per 1M characters: ↑ what you send.

MinimaxUnited States…
↑
19 970,14
Latency
…
Provider↑ SentLatencyUptime
MinimaxUnited States19 970,14……

You pay the price of the provider that served your request. Prices read 15:20 · 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/speech
Base URL
https://opendunes.com/v1
Model ID
minimax/speech-2.8-turbo
import os
from openai import OpenAI

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

with client.audio.speech.with_streaming_response.create(
    model="minimax/speech-2.8-turbo",
    input="مرحبا بكم في متجرنا. التوصيل مجاني في وهران.",
    voice="English_expressive_narrator",
) as resp:
    resp.stream_to_file("speech.mp3")
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Questions about Speech 2.8 Turbo

  • How much does Speech 2.8 Turbo cost in dinars?

    About 11,98 DA per paragraph read aloud. ↑ 19 970,14 DA per 1M characters.

  • Is Speech 2.8 Turbo 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 Speech 2.8 Turbo best for?

    MiniMax Speech 2.8 Turbo turns text into speech and returns audio, using any MiniMax voice you name, with the same abilities as the HD version: emotion settings and tags for laughs and sighs written into the text. It is tuned for speed, so it fits assistants and apps that speak replies as they are produced.

  • Speech 2.8 Turbo or Speech 2.8 HD?

    Speech 2.8 HD costs 7,99 DA more for the same paragraph read aloud.

  • How do I pay for Speech 2.8 Turbo without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Speech 2.8 Turbo included, is paid from that balance. No foreign card, no conversion.

  • Does Speech 2.8 Turbo work in Arabic, French or Darja?

    MiniMax says Speech 2.8 supports 40 languages, and its API language options include Arabic and French. Darja is not named.

  • How many voices, and can it clone mine?

    45 voices. Cloning from a sample: not stated.

  • Who makes Speech 2.8 Turbo, and when was it released?

    MiniMax. Released 16 July 2026.

Other MiniMax models, priced in dinars

See all MiniMax models
MiniMax M3.1 FlashMiniMax · Oct 19, 2026

This model accepts text, pictures, and video inputs, and can process up to 1000 pages of information to generate responses up to 520 pages long. It excels at complex tasks like coding, cybersecurity, and advanced problem-solving. Its ability to handle video input and its high ranking in reasoning set it apart from other models. However, it cannot search the web or structure data into specific formats.

Thinks firstUses your tools1 000 pages at once
≈0,15 DAper message
View model
H3MiniMax · Jul 29, 2026

MiniMax H3 edits and generates video from text, pictures, video and audio, with 2K output, built-in sound and clips of 5 to 15 seconds. It follows written edit instructions, shows text and logos legibly and copies motion from one video to another, which suits ads, product videos and game or app mockups. You can fix the first and last frames.

Makes soundAnimates your photoFirst + last frame
43,27 DAper second of video
View model
Speech 2.8 HDMiniMax · Jul 16, 2026

MiniMax Speech 2.8 HD turns text into speech and returns audio, using any MiniMax voice you name. It is the quality tier: it voices laughs and sighs written into the text as tags, and it supports emotion settings like happy, sad or calm. Use it for narration, audiobooks and finished voice-overs.

45 voices
≈19,97 DAper paragraph read aloud
View model
Hailuo 2.3MiniMax · Apr 20, 2026

MiniMax's Hailuo 2.3, aimed at cinematic scenes and character animation where motion must look real and characters expressive, producing 6 or 10 second 1080p clips from a prompt or an opening image

Animates your photoUp to 10 s1080p
27,19 DAper second of video
View model