161B
- Pricing
- Not published
- Released
- 7mo ago
Cost
MiMo-V2-TTS is a text-to-speech model from Xiaomi, released as part of the MiMo-V2 series and later succeeded by the MiMo-V2.5-TTS lineup. Xiaomi's launch notes state that it was pretrained on more than 100 million hours of data. The model is built for speech synthesis, turning written text into spoken audio.
How it compares
Additional source evidence
- Source model
- xiaomi/mimo-v2-tts
- Source family
- mimo
- Source type
- speech
- Last updated
- 2026-03-18
- Model context
- 8K
- Model output limit
- 8K
- Open weights
- No
- File attachments
- No
- Reasoning
- No
- Tool calling
- No
- Temperature control
- No
Complete source record (JSON)
{
"id": "xiaomi/mimo-v2-tts",
"name": "MiMo-V2-TTS",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"family": "mimo",
"type": "speech",
"last_updated": "2026-03-18",
"attachment": false,
"reasoning": false,
"tool_call": false,
"temperature": false,
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"release_date": "2026-03-18",
"open_weights": false
}Frequently asked questions
Quality and benchmarks
The closest alternatives are Suno v5.5 by Suno, Grok TTS by xAI, and Stable Audio 3.0 Large by Stability AI. They were matched on model kind and release date, with no comparable price listed.
Suno v5.5MiMo-V2-TTS vs Suno v5.5Grok TTSMiMo-V2-TTS vs Grok TTSStable Audio 3.0 LargeMiMo-V2-TTS vs Stable Audio 3.0 Large
Licensing and access
No, MiMo-V2-TTS is closed. It is neither open source nor open weights.
Basics
MiMo-V2-TTS was made by Xiaomi and released on March 18, 2026.
Generated from Vertical Tabs data, updated November 2, 2026.
Discussion
No comments yet
Be the first to share your thoughts.