MiMo-V2.5-TTS-VoiceClone
Xiaomi text-to-speech that clones a target voice from a few seconds of reference audio, with style instructions and cross-lingual cloning.
Specs
- Context
- 8.2K
- Max output
- 8.2K
- Input price
- —
- Output price
- —
- Released
- 2026-04-23
Context
- Context window
- 8.2K
- Max input
- —
- Max output
- 8.2K
Pricing
- Not published
Modalities
- Input
- TextAudio
- Output
- Audio
API
- API types
Reasoning
- Reasoning
- No
Info
- Status
- Active
- Released
- 2026-04-23
- Knowledge cutoff
- —
Features
- Confirmed
How to call
1 provider
xiaomimodel = mimo-v2.5-tts-voiceclone
messages
POSThttps://api.xiaomimimo.com/v1/chat/completions
JSON
Standard format
{
"id": "mimo-v2.5-tts-voiceclone",
"object": "model",
"created": 1776902400,
"owned_by": "xiaomi",
"name": "MiMo-V2.5-TTS-VoiceClone",
"api": {
"types": [
"audio"
]
},
"limits": {
"context": 8192,
"input": null,
"output": 8192
},
"modalities": {
"input": [
"text",
"audio"
],
"output": [
"audio"
]
},
"reasoning": {
"supported": false,
"efforts": []
},
"pricing": null,
"features": [
"streaming"
],
"info": {
"status": "active",
"release_date": "2026-04-23",
"knowledge_cutoff": null,
"description": "Xiaomi text-to-speech that clones a target voice from a few seconds of reference audio, with style instructions and cross-lingual cloning.",
"docs": "https://mimo.mi.com/models/zh-CN/mimo-v2.5-tts-voiceclone",
"verified_at": "2026-10-11"
}
}Official sources
3