MiniMax: Speech 2.8 HD
by MiniMax · Released 2026-07-16
MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.
Released2026-07-16
What it can do
What this model can take in, what it replies with, and what it does not do.
Not for
- Fine-tuning on your own data — not supported
Also supports
Tool callingStructured JSONStep-by-step reasoningStreamingPrompt cachingFine-tuning
Where your request runs
You call one endpoint. Behind it, OpenDunes keeps every one of these live — if one degrades, the next takes the request without you changing a line.
| Provider | In /M | Out /M | Cache /M | Latency | TPS | Uptime |
|---|---|---|---|---|---|---|
| Minimax | 32 400 DA | Free | — | — | — | 100,0 % |
Routed through the Bifrost gateway · prices in Algerian Dinars per 1M tokens · you’re charged the price of the endpoint that served your request.
What it costs
Each request charges exactly what it uses — no subscription, no minimum.
32 400 DA / 1M chars
Top up points
3 000 DA ≈ 308 typical replies · the exact charge appears after every request, down to the centime.
Call it in code
OpenAI-compatible — point any OpenAI SDK at our base URL and keep your code. Copy the request, or run it right here on your wallet.
Sign in to run this request on your own wallet.
The same request, in your language
Parameters you can send
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Limits
The hard numbers — what it can take in, what it can give back, and where it stops.
- Tokenizer
- Other
- Released
- 2026-07-16
Questions about Speech 2.8 HD
What can Speech 2.8 HD handle?
It reads text and replies with audio.
Can I use Speech 2.8 HD without an international bank card?
Yes. Top up your OpenDunes balance in dinars with a CIB or Edahabia card, then spend it on Speech 2.8 HD or any other model in the catalog from that same balance. No foreign card, no currency conversion, no subscription.
Who makes Speech 2.8 HD?
Speech 2.8 HD is built by MiniMax, released on Jul 16, 2026. OpenDunes serves it unchanged — same model, same weights, billed in dinars.
Other MiniMax models, priced in dinars
See all MiniMax modelsMiniMax: H3 Max
minimax/hailuo-3-maxVideo
MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...
TextImagesVideo
16,20 DA / secby MiniMaxSep 2, 2026
MiniMax: H3
minimax/hailuo-3Video
MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...
TextImagesVideoAudioVideo
42,12 DA / secby MiniMaxJul 29, 2026
MiniMax: Speech 2.8 Turbo
minimax/speech-2.8-turboSpeech
MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.
TextAudio
19 440 DA / 1M charsby MiniMaxJul 16, 2026
MiniMax: MiniMax M3
minimax/minimax-m3Text
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
TextImagesVideoText
in97,20 DAout388,80 DAper 1M tokens
by MiniMaxMay 31, 20261M contextReasoningToolsJSON
MiniMax: MiniMax M3 (batch)
minimax/minimax-m3:batchText
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
TextImagesVideoText
in97,20 DAout388,80 DAper 1M tokens
by MiniMaxMay 31, 2026524K contextReasoningToolsJSON
MiniMax: Hailuo 2.3
minimax/hailuo-2.3Video
Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows. It is...
TextImagesVideo
26,47 DA / secby MiniMaxApr 20, 2026
MiniMax: MiniMax M2.7
minimax/minimax-m2.7Text
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
TextText
in97,20 DAout388,80 DAper 1M tokens
by MiniMaxMar 18, 2026205K contextReasoningToolsJSON
MiniMax: MiniMax M2.5
minimax/minimax-m2.5Text
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
TextText
in87,48 DAout349,92 DAper 1M tokens
by MiniMaxFeb 12, 2026205K contextReasoningToolsJSON