{"id":195340,"date":"2025-09-02T23:34:10","date_gmt":"2025-09-02T23:34:10","guid":{"rendered":"https:\/\/www.europesays.com\/us\/195340\/"},"modified":"2025-09-02T23:34:10","modified_gmt":"2025-09-02T23:34:10","slug":"microsoft-unveils-vibevoice-for-longer-conversational-ai-audio","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/us\/195340\/","title":{"rendered":"Microsoft Unveils VibeVoice for Longer Conversational AI Audio"},"content":{"rendered":"

Microsoft<\/a> has released<\/a> VibeVoice, a new open-source artificial intelligence (AI) model that lets users create podcasts and other audio \u2014 a counter to Google<\/a>\u2019s popular NotebookLM<\/a>.<\/p>\n

But there are notable differences. Microsoft\u2019s text-to-speech model can generate four voices and up to 90 minutes of podcast-quality speech. NotebookLM can do two voices.<\/p>\n

Additionally, VibeVoice reads and organizes text while NotebookLM ingests documents and turns them into two-person podcasts. Users can also query and get document summaries, according to tech firm Hugging Face<\/a>.<\/p>\n

That means VibeVoice doesn\u2019t try to understand the text but rather performs it audibly, ostensibly to replace a recording studio.<\/p>\n

VibeVoice is the latest offering in voice AI technology, which has been attracting venture capital funding. <\/p>\n

In 2024, voice AI startups raised<\/a> $2.1 billion, up eightfold from the prior year, according to market research firm CB Insights<\/a>. There\u2019s rising interest in voice shopping: A PYMNTS Intelligence report<\/a> shows that 30.4% of Gen Z consumers already shop by voice every week, followed by millennials. For all ages, the average is 17.9% of consumers using voice to shop.<\/p>\n

VibeVoice runs on 1.5 billion parameters, relatively small for a model capable of sustaining dialogue across multiple speakers. <\/p>\n

It was trained using Alibaba\u2019s open-source Qwen2.5, a large language model that helps orchestrate natural turn-taking and contextually aware speech patterns during dialogues. <\/p>\n

Microsoft claims this means VibeVoice can produce fluid conversations among four voices and yet maintain each voice\u2019s distinct characteristics, even in longer conversations.<\/p>\n

See also<\/strong>: How the World Does Digital: A Deep Dive Into Global Digital Engagement<\/a><\/p>\n

How to use VibeVoice<\/strong><\/p>\n

Potential research applications of VibeVoice include the following:<\/p>\n

Prototyping podcasts and training content<\/p>\n