MiniMax Speech Models by MiniMax
1 model2024
Last refreshed 2026-06-15. Next refresh: weekly.
About
MiniMax Speech is MiniMax's family of text-to-speech (TTS) models, offering high-quality voice synthesis across multiple languages and speaking styles.
Decision facts
- Best fit
- text to speech
- Capability starting point
- MiniMax Speech 2.8
- Lowest tracked input
- Not tracked
- Closest related family
- MiniMax Image
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
MiniMax Speech 2.8Current
Use when the workload needs text to speech and audio.
2024-10text to speechaudio
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| MiniMax Speech 2.8 | Use when the workload needs text to speech and audio. | 2024-10 | text to speechaudio | Current |
Release Timeline
1 release group2024-10
1 current
MiniMax Speech 2.8
Currenttext to speechaudio
Specifications(1 models)
| Model | Released |
|---|---|
| MiniMax Speech 2.8 | 2024-10 |
