MiMo-V2.5-TTS-VoiceClone

The MiMo-V2.5-TTS-VoiceClone model specializes in voice synthesis with precise cloning capabilities. By accepting text input, it produces natural, fluent speech output that mirrors the characteristics of provided audio samples. This enables developers and creators to replicate any voice for synthesis purposes, with configurable parameters for speech style and voice characteristics to suit different use cases.

As part of Xiaomi's MiMo-V2.5 series, this speech synthesis model benefits from the broader family architecture that also includes general base models and other TTS variants like voice design tools. The open-weights approach makes it freely accessible, aligning with the free-tier offering highlighted by the hosting platform. This positions the voice cloning model as an entry point for experimentation and integration into applications requiring authentic voice replication without licensing barriers.

Xiaomi Token Plan (China)mimo-v2.5-tts-voiceclonemimo

Open provider page Provider docs

Quick Info

Provider: Xiaomi Token Plan (China)
Model key: mimo-v2.5-tts-voiceclone
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-VoiceClone

Xiaomi Token Plan (China)

Official sourceDocumentation

According to Xiaomi's official MiMo platform changelog (dated 2026-04-23), five new models were added to all Token Plan tiers, explicitly including mimo-v2.5-tts-voiceclone alongside mimo-v2.5-pro, mimo-v2.5, mimo-v2.5-tts-voicedesign, and mimo-v2.5-tts. The update also removed tiered token consumption based on context The same update notes that mimo-v2.5-tts-voiceclone was made available alongside Xiaomi's broader V2.5 release, which followed by about 36 days the prior V2 release and was led by MiMo head Luo Fuli. While the changelog does not enumerate VoiceClone-specific technical parameters, its explicit naming of the variant esta

Xiaomi Token Plan (China)

Coverage

AIbase's coverage describes Xiaomi's MiMo-V2.5 Full-Stack Speech Model Series launch, explicitly naming MiMo-V2.5-TTS-VoiceClone as a model that high-fidelity replicates a target voice from only a small sample (e.g., 30 seconds of audio) while retaining the ability to respond to style instructions and audio tags. The a The same piece explains that VoiceClone is part of a three-TTS-model lineup released alongside an open-source MiMo-V2.5-ASR model, with VoiceDesign handling text-prompted voice generation and the base V2.5-TTS offering built-in premium voices controllable via natural-language instructions like directing an actor. Suppo