MiniMax

About MiniMax

Overview of MiniMax AI models and their capabilities

Website ↗GitHub ↗Documentation ↗

Source ↗ · 2026-10-24T08:34:50.638378719Z

Service status

operational

LLM, text-to-speech and video generation

Official status page ↗

33 indexed models

33 matching models

MiniMax: Speech 2.8 HD

minimax/speech-2.8-hd-20260716

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.

Context window
0
Input modalities
text
Output modalities
speech
Capabilities
speechOutput

Inference prices

  • Per 1M characters : $100.00 / characters_per_million · miniMax ↗

MiniMax: Speech 2.8 Turbo

minimax/speech-2.8-turbo-20260716

MiniMax Speech 2.8 Turbo 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.

Context window
0
Input modalities
text
Output modalities
speech
Capabilities
speechOutput

Inference prices

  • Per 1M characters : $60.00 / characters_per_million · miniMax ↗

music-2.6-free

miniMax/music-2.6-free

Input modalities
text
Output modalities
audio
Capabilities
audioOutput, musicGeneration

music-3.0

miniMax/music-3.0

• New Music Generation Capabilities

Input modalities
text
Output modalities
audio
Capabilities
audioOutput, musicGeneration

music-3.0-free

miniMax/music-3.0-free

Input modalities
text
Output modalities
audio
Capabilities
audioOutput, musicGeneration

music-cover

miniMax/music-cover

• Generate cover versions from reference audio

Input modalities
audio, text
Output modalities
audio
Capabilities
audioInput, audioOutput, multimodal, musicGeneration

music-cover-free

miniMax/music-cover-free

Input modalities
audio, text
Output modalities
audio
Capabilities
audioInput, audioOutput, multimodal, musicGeneration

speech-01-hd

miniMax/speech-01-hd

Input modalities
text
Output modalities
speech
Capabilities
speechOutput

speech-01-turbo

miniMax/speech-01-turbo

Input modalities
text
Output modalities
speech
Capabilities
speechOutput

speech-02-hd

miniMax/speech-02-hd

• Stronger replication similarity; • High quality voice generation

Input modalities
text
Output modalities
speech
Capabilities
speechOutput

speech-02-turbo

miniMax/speech-02-turbo

• Superior rhythm and stability; • Low latency

Input modalities
text
Output modalities
speech
Capabilities
speechOutput

speech-2.6-hd

miniMax/speech-2.6-hd

• Ultimate Similarity; • Ultra-High Quality

Input modalities
text
Output modalities
speech
Capabilities
speechOutput

speech-2.6-turbo

miniMax/speech-2.6-turbo

• Ultimate Value; • Low latency

Input modalities
text
Output modalities
speech
Capabilities
speechOutput

T2V-01

miniMax/T2V-01

Input modalities
text
Output modalities
video
Capabilities
videoOutput

T2V-01-Director

miniMax/T2V-01-Director

Input modalities
text
Output modalities
video
Capabilities
videoOutput

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace