Speech 2.8 HD

by MiniMaxSpeech synthesis

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.

00
Released
2026-07-16
Weights
unknown

Feed

minimax/speech-2-8-hd

Specifications

Full facts as recorded, incl. what is unknown.

Released
2026-07-16
Weights
unknown
Input
Text
Output
speech
Context window
max across endpoints
Max output
Providers
0 + 1 gateway, not counted as providers
Epoch Capabilities Index
not evaluated
Direct price range
no comparable direct price
More details
Last updated
—
Knowledge cutoff

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool callingunknown
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoningunknown
  • Image inputunknown
  • PDF inputunknown
  • Audio inputunknown
  • Audio outputunknown
  • Video inputunknown
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperatureunknown
  • Streamingunknown
  • Attachmentsunknown

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Cost calculator

Loading endpoints…

More from MiniMax

Newest MiniMax models in the catalogue. All MiniMax models

ModelReleasedContextListed price
MiniMax-M3.1-Flash2026-10-191Mfrom $0.15 /1M tok
MiniMax-M3.1-Flash-Preview2026-09-271Munpriced
H3 Max2026-09-02—unpriced
MiniMax H3 Max2026-08-27—unpriced
MiniMax H32026-07-31—unpriced
H32026-07-29—unpriced
Speech 2.8 Turbo2026-07-16—unpriced
MiniMax M3 Preview2026-06-12524Kfrom $0.30 /1M tok
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model