NewGPT Image 2.6, Kling V4 and Kimi K3.1 Pro are now available.

Tchavi
ModelsPricingDocumentationBlog
Tchavi
  • Why Tchavi
  • Models
  • Pricing

Tchavi is an OpenAI-compatible AI API: 130+ models, from text to video, topped up with mobile money in FCFA or your local currency, no bank card needed.

  • support@tchavi.com
  • Support

Popular models

  • GPT-6 Sol API
  • Claude Sonnet 5.5 API
  • Claude Opus 5.5 API
  • Gemini 4 Argon API
  • DeepSeek V4.1 Flash API
  • Nano Banana 2.1 (images)
  • GPT Image 2 (images)
  • Wan 3.0 (video)
  • All 130+ models

Developers

  • Quickstart
  • API Reference
  • Claude Code
  • Cursor
  • SDKs

Resources

  • Documentation
  • Blog
  • Image models
  • Video models
  • Music models
  • Audio models
  • Mobile money payments
  • Pay for AI APIs with M-Pesa
  • Claude Code with mobile money

Legal

  • Privacy
  • Terms of Service

APIs by creator

  • OpenAI API
  • Gemini API
  • Claude API
  • Qwen API
  • DeepSeek API
  • Seedance API
  • MiniMax API
  • Mistral API

Mobile money payments · Available in 12 countries: Benin, Cameroon, Congo, Côte d'Ivoire, DR Congo, Gabon, Kenya, Rwanda, Senegal, Sierra Leone, Uganda, and Zambia. Operators: Moov Money, MTN MoMo, Airtel Money, Orange Money, M-Pesa, Free Money, and Zamtel Kwacha.

© 2026 Tchavi. All rights reserved.

We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.

Back to models
M

MiniMax Speech 2.8 HD

minimax/minimax-speech-2.8-hd

The studio voice, in forty languages

MiniMax's current high-fidelity voice, billed per character like the rest of our text-to-speech: 219.495 credits per 1 000 characters. It speaks more than forty languages, takes a speed between 0.5 and 2, and answers in mp3, wav, flac or raw PCM.

Modalities
Input / Output
219.495 / 0cr / 1K
Available voices
20
Released
Oct 20, 2026

What this model does well

  • 🌍

    Multilingual

    Over forty languages, French and English included

  • 🔤

    Per character

    You are billed for the characters you send, not for the audio length

  • 🎚️

    Four formats

    mp3, wav, flac or raw PCM

  • ⏩

    Adjustable speed

    0.5x to 2x, set per request

  • 🎁

    Free tier

    In the BUDGET group — a free account can call it

Good to know

  • Dearer than the ElevenLabs voices beside it (219.495 against 175.596 per 1 000 characters). Carried for its voices and its languages, not for its price.
  • Give it a voice id. `English_Wiselady` is the default; MiniMax's own voice ids and ids from its voice cloning both work, and an unknown one is refused by the provider.
  • No `instructions` and no `language` parameter: MiniMax has neither, and we do not invent them.
  • Text in, audio out. It does not listen.

Technical specifications

Provider
MiniMax
API identifier
minimax-speech-2.8-hd
Category
Audio
Available voices
French_CasualMan, French_FemaleAnchor, French_Female_News Anchor, French_Male_Speech_New, French_MaleNarrator, French_MovieLeadFemale, English_Wiselady, English_Debator, English_LovelyGirl, English_Steadymentor, English_Deep-VoicedGentleman, English_CaptivatingStoryteller, English_DecentYoungMan, English_SentimentalLady, English_ImposingManner, English_SadTeen, English_PassionateWarrior, English_WiseScholar, English_Soft-spokenGirl, English_SereneWoman
Rate limit
30 RPM
Billing unit
character

Ideal for

  • Voice replies to customer messages, in French
  • Narration for a product video
  • Reading a payment confirmation aloud in an IVR
  • Audio versions of articles
  • Any language ElevenLabs does not cover

Ready to try it?

Test this model in the playground, no setup needed.

Frequently asked questions

Can I pay with mobile money, without a bank card?

Yes. Top up your Tchavi account with Orange Money, MTN MoMo, M-Pesa or another mobile money operator. No bank card is needed. Credits land as soon as the payment is confirmed and are deducted as you use them.

Is the API compatible with OpenAI's?

Yes. Keep your current OpenAI SDK, just change the base URL to Tchavi's (shown in the API tab) and use your Tchavi key. The rest of your code stays the same.

API

import Tchavi from '@tchavi/sdk';
import fs from 'fs';

const client = new Tchavi({ apiKey: 'API_KEY' });

const response = await client.audio.speech.create({
  "model": "minimax-speech-2.8-hd",
  "input": "Hello, world!",
  "voice": "French_CasualMan",
  "response_format": "mp3"
});

const buffer = Buffer.from(await response.arrayBuffer());
fs.writeFileSync('speech.mp3', buffer);
console.log('X-Credits-Used:', response.headers.get('x-credits-used'));

API parameters

Every parameter this model accepts on the API. Check the SDK for full typings.

modelRequired
string

TTS model (e.g. `minimax-speech-2.8-hd`).

inputRequired
string

The text to synthesize.

voiceRequired
string

Voice timbre: `alloy`, `ash`, `ballad`, `cedar`, `coral`, `echo`, `fable`, `marin`, `nova`, `onyx`, `sage`, or `shimmer`.

response_format
"mp3" | "wav" | "flac" | "pcm"
Default: "mp3"

Audio container format.

Show all parameters (5)
speed
number (0.25–4.0)
Default: 1.0

Playback speed multiplier.

Pricing

per 1,000 characters
219.495 credits

How billing works

  • Billed per thousand characters.
  • A typical generation costs about —, or 219.495 credits.
Per day
Per week
Per month
A 10 000 F CFA top-up gives you about ~136 thousand characters. Pay with Orange Money, MTN MoMo or M-Pesa — no Visa card needed.

Ready to use MiniMax Speech 2.8 HD?

Create your accountAPI Documentation

Bonus credits on your first top-up · No card to sign up