Oct. 29, 2025
Music-2.0
Released Music 2.0, enhanced musical expression that makes every melody deeply emotional.
Oct. 29, 2025
Speech-2.6
Released Speech 2.6 — More human and instantly responsive voice for your agent.
Oct. 28, 2025
MiniMax-Hailuo-2.3 & 2.3-Fast
Released MiniMax-Hailuo-2.3 & 2.3-Fast, featuring breakthroughs in body movement, facial expressions, physical realism, and prompt adherence.
Oct. 27, 2025
MiniMax-M2
MiniMax-M2 Released. An Efficient Model for the Agentic Era.
Get free MiniMax M2 model API calls now. Offer ends November 7, 2025, at 00:00 UTC.
Get free MiniMax M2 model API calls now. Offer ends November 7, 2025, at 00:00 UTC.
Sept. 11, 2025
Music-1.5
New music model released. Now supports 4-minute songs, getting back to the core of great sound.
Aug. 6, 2025
Speech-2.5
Released a next-generation speech synthesis model featuring broader language coverage and exceptionally high voice similarity.
Jun. 20, 2025
Music-1.5 (Beta)
Released Music-1.5 (Beta), a next-generation music generation model that supports creating music from musical prompts and lyrics.
Jun. 18, 2025
MiniMax-Hailuo-02
Released MiniMax Hailuo 02, a next-generation video generation model with support for 1080p resolution and video generation of up to 10 seconds.
Apr. 2, 2025
Speech-02-turbo / Speech-02-hd
Released the Speech-02 model series, delivering hyper-realistic vocal performance. The models are distinguished by exceptional prosody and stability, along with outstanding voice similarity and audio quality.
Feb. 15, 2025
Image-01
Released the Image-01 model, which supports text-to-image generation in multiple sizes.
Feb. 11, 2025
T2V-01-Director / I2V-01-Director
Released a video generation model with enhanced camera control, offering superior adherence to camera movement directives and enabling cinematic storytelling through its shot composition.
Jan. 15, 2025
MiniMax-Text-01 / MiniMax-VL-01
Released the next-generation text model, MiniMax-Text-01, and the vision-language model, MiniMax-VL-01.