# MiMo-V2.5-TTS-VoiceClone

> MiMo-V2.5-TTS-VoiceClone is a proprietary speech model from Xiaomi (MiMo), released on 22 Apr 2026. It accepts text and generates audio, with a 8K-token context window and up to 8K output tokens per response.

Source page: https://www.aimodel.directory/models/mimo-v2-5-tts-voiceclone
Last verified: 21 Oct 2026

## Specifications

- **Developer:** Xiaomi (MiMo)
- **Release date:** 22 Apr 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)
- **Context window:** 8K (8,192 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)
- **Max output:** 8K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)
- **Output:** Audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi-token-plan-cn/models/mimo-v2.5-tts-voiceclone.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of MiMo-V2.5-TTS-VoiceClone?

MiMo-V2.5-TTS-VoiceClone has a context window of 8,192 tokens (8K) and can generate up to 8,192 tokens in a single response, according to models.dev.

### Is MiMo-V2.5-TTS-VoiceClone open source?

No. MiMo-V2.5-TTS-VoiceClone is a proprietary model; Xiaomi (MiMo) has not released its weights.

### When was MiMo-V2.5-TTS-VoiceClone released?

Xiaomi (MiMo) released MiMo-V2.5-TTS-VoiceClone on 22 Apr 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "MiMo-V2.5-TTS-VoiceClone", https://www.aimodel.directory/models/mimo-v2-5-tts-voiceclone