161B
- Pricing
- Not published
- Released
- 6mo ago
Cost
Speech generation model for controllable voice, narration, and audio delivery
How it compares
Additional source evidence
- Source model
- xiaomi/mimo-v2.5-tts
- Source family
- mimo
- Source type
- speech
- Last updated
- 2026-04-22
- 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-v2.5-tts",
"name": "MiMo-V2.5-TTS",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"family": "mimo",
"type": "speech",
"last_updated": "2026-04-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"temperature": false,
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"release_date": "2026-04-22",
"open_weights": false
}Frequently asked questions
Quality and benchmarks
The closest alternatives are Stable Audio 3.0 Large by Stability AI, GPT Realtime Whisper by OpenAI, and AFM 3 Core Advanced by Apple. They were matched on model kind and release date, with no comparable price.
Stable Audio 3.0 LargeMiMo-V2.5-TTS vs Stable Audio 3.0 LargeGPT Realtime WhisperMiMo-V2.5-TTS vs GPT Realtime WhisperAFM 3 Core AdvancedMiMo-V2.5-TTS vs AFM 3 Core Advanced
Licensing and access
No, MiMo-V2.5-TTS is closed.
Basics
MiMo-V2.5-TTS was made by Xiaomi and released on April 22, 2026.
Generated from Vertical Tabs data, updated November 9, 2026.
Discussion
No comments yet
Be the first to share your thoughts.