---
name: Mimo-V2.5-Tts-Voicedesign
slug: mimo-v2-5-tts-voicedesign
type: Multimodal
providers:
  - xiaomi-token-plan-cn
description: 'Speech generation model for controllable voice, narration, and audio delivery'
tags:
  - open-source
  - mimo
  - multimodal
is_open_source: true
context_window: 8192
max_output: 8192
pricing:
  - image: 0
    input: 0
    output: 0
    provider: xiaomi-token-plan-cn
release_date: '2026-04-22'
capabilities:
  audio: false
  vision: false
  tool_use: false
  citations: false
  reasoning: false
---
Mimo-V2.5-Tts-Voicedesign is a Multimodal model.
Speech generation model for controllable voice, narration, and audio delivery