Base44
Mini toolsVibeVoice
By Microsoft
VibeVoice is Microsoft’s open-source long-form text-to-speech model and framework, able to synthesize up to roughly 90 minutes of multi-speaker audio from text. It uses ultra-low-rate acoustic and semantic speech tokenizers to keep quality while scaling to long dialogues, supports several model sizes like VibeVoice-1.5B, and targets podcast-style conversations, dialogue generation and accessibility use cases, with an online demo and Hugging Face deployment options.
New
Audio
Gen 4
Overview
VibeVoice is Microsoft’s open-source frontier TTS framework that turns long text into expressive multi-speaker conversational audio, generating podcast-style speech with natural turn-taking in English and Mandarin
About Microsoft
Microsoft is a technology company that offers a wide range of software, cloud computing services, hardware, and artificial intelligence solutions.
Industry:
Software Development
Company Size:
228000+
Location:
Redmond, Washington, US
Website:
microsoft.com
Tools using VibeVoice
No tools found for this model yet.
Last updated: December 9, 2025
