As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/minimax-speech-2-8/

# MiniMax Speech 2.8 (HD / Turbo)

MiniMax, MiniMax Speech family. Status: current. Type: speech and audio. Released: 2026-01-23.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| MiniMax API (T2A HTTP / WebSocket / async) | `speech-2.8-hd` | https://api.minimax.io | https://platform.minimax.io/docs/api-reference/speech-t2a-http |
| MiniMax API | `speech-2.8-turbo` | https://api.minimax.io | https://platform.minimax.io/docs/api-reference/speech-t2a-http |
| Web app (MiniMax Audio) |  |  | https://www.minimax.io/audio |

## Pricing

- Per 1M characters, HD: $100
- Per 1M characters, Turbo: $60
- Unit as published: USD per 1M characters (sync and async T2A). Voice clone 1.5 USD/voice, voice design 3 USD/voice
- Source: https://platform.minimax.io/docs/guides/pricing-paygo
- Last checked: 2026-09-29

## Specs

- Input: text
- Output: audio
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 70. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Closed weights; access is hosted only.

## What stands out

- Sound tags: Natural sound tags (non-verbal cues) in ultra-realistic HD speech. Source: https://platform.minimax.io/docs/release-notes/models
- 40 languages, 7 emotions: 40 languages plus specified dialects, 7 emotions; rapid voice cloning and text-described voice design. Source: https://platform.minimax.io/docs/guides/models-intro
- Streaming and long-form modes: Sync HTTP, WebSocket and bidirectional streaming (pipe LLM tokens straight to speech), plus async jobs up to 1M characters. Source: https://platform.minimax.io/docs/guides/pricing-paygo

## Notes

speech-2.6 and speech-02 are legacy at the same prices. MiniMax also offers ASR (0.38 USD/hour). Music: music-3.0 API closed to new users from 2026-08-20; open weights MiniMax-Music3 on HF.

MiniMax's current TTS: expressive multilingual voices, cloning and real-time streaming for agents, audiobooks and dubbing.

Sources: https://platform.minimax.io/docs/guides/models-intro · https://platform.minimax.io/docs/guides/pricing-paygo · https://platform.minimax.io/docs/api-reference/speech-t2a-http

Model page: https://postcutoff.com/m/minimax-speech-2-8/