MAI-Voice-2.1-Flash
低延迟、富有表现力的文字转语音模型，支持 23 种语言，面向实时语音智能体，通过 Azure Speech SSML 使用。
规格
- 上下文
- —
- 最大输出
- —
- 输入价
- —
- 输出价
- —
- 发布日期
- —
上下文
- 官方未公布
价格
- 官方未公布
输入输出
- 输入
- 文本
- 输出
- 音频
API
- 接口类型
思考
- 官方未公布
源信息
- 状态
- 预览
- 发布日期
- —
- 知识截止
- —
能力
- 官方未公布
调用方式
1 个 Provider
microsoftmodel = MAI-Voice-2.1-Flash
audio
POSThttps://<region>.tts.speech.microsoft.com/cognitiveservices/v1
JSON
标准格式
{
"id": "mai-voice-2.1-flash",
"object": "model",
"created": null,
"owned_by": "microsoft",
"name": "MAI-Voice-2.1-Flash",
"api": {
"types": [
"audio"
]
},
"limits": {
"context": null,
"input": null,
"output": null
},
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": null,
"features": [],
"info": {
"status": "preview",
"release_date": null,
"knowledge_cutoff": null,
"description": "Low-latency expressive text-to-speech model across 23 languages for real-time voice agents, used via Azure Speech SSML.",
"docs": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-voices",
"verified_at": "2026-10-11"
}
}官方来源
2