MiMo-V2.5-TTS-VoiceDesign

MiMo V2.5 TTS VoiceDesign is a text-to-speech model from Xiaomi's MiMo V2.5 series focused on voice design, letting users shape customizable speech output rather than simply read text aloud. It accepts text as input and produces audio as output, positioning it as a creative and product-facing synthesis tool within Xiaomi's broader V2.5 lineup. The variant is listed as Active by third-party catalogs and is one of five V2.5 models added to Xiaomi's Token Plan subscription tiers in the same rollout, sitting alongside V2.5 Pro, V2.5 base, and the related TTS offerings.

Practically, the model is aimed at builders who need controllable voice personas for applications such as assistants, narration, branded content, and prototyping multilingual voice experiences, fitting naturally into Xiaomi's Token Plan ecosystem with monthly and annual auto-renewal options. Its inclusion in the V2.5 series matters because Xiaomi removed the prior tiered context-length token surcharge for the family, simplifying cost planning for longer prompts. With the older V2 series deprecated and users being directed to migrate to V2.5, VoiceDesign represents Xiaomi's current-generation path for designer-driven speech synthesis.

Xiaomi Token Plan (Singapore)mimo-v2.5-tts-voicedesignmimo

Open provider page Provider docs

Quick Info

Provider: Xiaomi Token Plan (Singapore)
Model key: mimo-v2.5-tts-voicedesign
Release date: Apr 22, 2026
Last updated: Apr 22, 2026
Input modalities
Output modalities
Capabilities

Cost

A provider subscription or plan supersedes token-based pricing for this model.

Limits

Output tokens: 8,192 tokens
Context window: 8,192 tokens

Latest news about MiMo-V2.5-TTS-VoiceDesign

Xiaomi Token Plan (Singapore)

Official sourceDocumentation

The Xiaomi MiMo platform update log records that on 2026-4-23, the Token Plan added five new models to all tiers, including "mimo-v2.5-tts-voicedesign" alongside mimo-v2.5-pro, mimo-v2.5, mimo-v2.5-tts-voiceclone, and mimo-v2.5-tts. The update also removed tiered token consumption based on context length across all mod The same update introduced subscription mechanics that frame the model's commercial context: monthly and annual auto-renewal plans with upgrade options, a returning-user usage-reset reward, first-time auto-renewal discounts (23% off for new users, 30% off for returning users), 12% annual-plan savings, and a 0.8x off-pe

Xiaomi Token Plan (Singapore)

Coverage

AIbase's coverage of Xiaomi's full-chain speech model launch explicitly names "MiMo-V2.5-TTS-VoiceDesign" as one of three TTS models, describing it as a system that can "generate a new voice with one sentence" from a text prompt such as "a 30-year-old intellectual female voice with a slight southern accent, suitable fo The article details a layered script mechanism in which character identity, scene atmosphere, and per-line performance guidance can be defined independently and updated separately while remaining consistent across an audiobook or game-NPC session, as well as inline audio tags that adjust emotion or delivery at specific