MiniMax Speech 2.8
TTS with native sound tags for human fillers, 10-second voice cloning, API-only.
About
MiniMax Speech 2.8 launched January 23, 2026 as the latest evolution of MiniMax's text-to-speech lineup, which holds a top position on the Artificial Analysis Speech Arena. Its headline feature is native sound tags: inline markers like um, uh, breaths, chuckles, and throat clears that render as authentic human vocalizations in the speech flow.
It adds 10-second voice cloning from a minimal sample, re-engineered noise removal for studio-grade clarity, and cross-lingual accent-bleed fixes starting with the Mandarin-Japanese pair. It ships in HD and Turbo variants via the MiniMax API; there are no open weights.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 105; Trending score 76/100 from researcher assessment.