微软MAI-Voice-2.1系列语音模型上线OpenRouter
微软AI的MAI-Voice-2.1与MAI-Voice-2.1-Flash语音模型已在OpenRouter平台上线。OpenRouter是一个支持多种AI模型访问与调用的平台。
两款模型均支持同一音色以23种语言母语口音发声。其中MAI-Voice-2.1-Flash针对低延迟与规模化场景优化，可在150毫秒内生成45秒音频，定价为每百万字符15美元；MAI-Voice-2.1定价为每百万字符22美元。该系列主要面向语音代理、智能助手、呼叫中心等实时语音与音频内容场景。
- 2026-10-02 02:33 | 华尔街见闻：微软上新三款语音AI模型：实时转文字准确率登测评榜首，MAI-Voice 2.1覆盖23种语言阅读原文
微软加速补齐语音AI能力。美东时间10月1日，微软发布三款新的语音模型，包括实时语音转文字模型 MAI-Transcribe-2-Streaming，以及文本转语音模型 MAI-Voice-2.1 和更低延迟的 MAI-Voice-2.1-Flash。其中，MAI-Transcribe-2-Streaming在AI基准测试平台Artificial Analysis的流式语音识别测试中拿下准确率第一。 AI基准测试与分析平台Artificial Analysis公布数据显示，MAI-Transcribe-2-Streaming的最终转录词错误率（WER）为2.5%，在38款模型中表现最佳；从说话...
- 2026-10-02 00:29 | X：MAI-Voice-2.1 from @MicrosoftAI is live on OpenRouter. MAI's highest-fidelity, most expressive text...阅读原文
MAI-Voice-2.1 from @MicrosoftAI is live on OpenRouter.MAI's highest-fidelity, most expressive text-to-speech model yet:• Studio-grade, natural speech.• Same voice can speak in 23 languages while maintaining native accent.• $22 per 1M charactersBuilt for audiobooks, podcasts, narration, and brand aud...
- 2026-10-02 00:28 | X：MAI-Voice-2.1-Flash from @MicrosoftAI is live on OpenRouter. MAI-Voice-2.1-Flash is optimized for s...阅读原文
MAI-Voice-2.1-Flash from @MicrosoftAI is live on OpenRouter.MAI-Voice-2.1-Flash is optimized for speed and scale:• Low-latency generation. Can generate 45s of audio within 150ms.• Natural, expressive speech with human-like intonation.• Same voice can speak in 23 languages while maintaining native ac...