MiniMax Speech 2.5
Multilingual expressiveness | Cloning fidelity
MiniMax-Hailuo-02
Start/End to Video | Native 1080p | SOTA Instruction Following
MiniMax M2
An Efficient Model for the Agentic Era
Models Overview
Text
| Models â â â â â | Description â â â â â | Features â â â â â â â â |
|---|---|---|
| MiniMax-M2 | ⢠Context Length: 200k tokens ⢠Maximum Output: 128k tokens (including CoT) | ⢠Agentic capabilities ⢠Function calling ⢠Advanced reasoning ⢠Real-time streaming |
| MiniMax-M1 | ⢠80K CoT Length ⢠1M max input tokens ⢠80K max output tokens | ⢠Streaming ⢠Function calling ⢠Reasoning |
Audio
| Models â â â â â â | Description â â â â â | Features â â â â â â â â â â â â â |
|---|---|---|
| speech-2.5-hd-preview | ⢠Ultimate Similarity ⢠Ultra-High Quality | ⢠40 languages supported ⢠7 emotions supported ⢠specified languages and dialects supported |
| speech-2.5-turbo-preview | ⢠Ultimate Value ⢠Low latency | ⢠40 languages supported ⢠7 emotions supported ⢠specified languages and dialects supported |
| speech-02-hd | ⢠Stronger replication similarity ⢠High quality voice generation | ⢠24 languages supported ⢠7 emotions supported ⢠specified languages and dialects supported |
| speech-02-turbo | ⢠Superior rhythm and stability ⢠Low latency | ⢠24 languages supported ⢠7 emotions supported ⢠specified languages and dialects supported |
Video
| Models â â â â â â | Description â â â â â â â â â | Res.& Dur. â â â â | FPS â â â â |
|---|---|---|---|
| MiniMax Hailuo 02 | ⢠Text to Video & Image to Video ⢠SOTA instruction following ⢠Extreme physics mastery | ⢠1080p 6s ⢠768p 6s, 10s ⢠512p 6s, 10s | 24 fps |
| T2V-01-Director | ⢠Text to Video ⢠Enhanced precision shot control | ⢠720p 6s | 25 fps |
| I2V-01-Director | ⢠Image to Video ⢠Enhanced precision shot control | ⢠720p 6s | 25 fps |
| S2V-01 | ⢠Image to Video ⢠Maintaining Character Consistency | ⢠720p 6s | 25 fps |