TOOLORA / Local reading edition
A speech-generation family whose current Speech 2.8 supports sound tags and reference-voice cloning through the platform or MiniMax Audio.
MiniMax Speech is a model family, separate from the multi-task MiniMax Audio product. Current Speech 2.8 supports tags for breaths, chuckles or throat clearing and reference-based voice cloning. Official examples demonstrate delivery and cross-language behavior. Access is offered through the platform or Audio; language coverage, cloning requirements and allowances depend on the chosen interface or plan.
MiniMax released M3.1 Flash for agent tasks, coding and computer use through its API, M Plan and MiniMax Code. The announcement schedules weights for later release rather than establishing immediate open-weight availability.
Products covered · MiniMax Language ModelsMusic 3.0 takes a creative description and optional lyrics. MiniMax describes a single generation covering composition, arrangement, vocals and production for songs up to five minutes. Its architecture separates global song structure from local acoustic detail and revises audio rendering.
Products covered · MiniMax MusicPublishes video-generation variants with different input formats, resolutions and generation methods.
Products covered · Hailuo AIDescriptions summarize public information; consult official websites for features, pricing and regional availability.
