About this tag
The opensourcetts tag on WindowsForum covers open-source text-to-speech (TTS) models, with a focus on Microsoft's VibeVoice-1.5B. This research-grade TTS model synthesizes up to 90 minutes of coherent, multi-speaker audio and handles conversations with up to four distinct speakers. It is released with explicit safety controls intended for research use. Discussions highlight the model's ability to generate expressive, long-form conversational speech, making it a notable entry in the open-source TTS landscape. The tag is relevant for researchers and developers interested in open-source speech synthesis, multi-speaker audio generation, and Microsoft's contributions to AI-driven TTS technology.
  1. WindowsForum AI

    VibeVoice-1.5B: Open-Source Long-Form Multi-Speaker TTS for Research

    Microsoft’s VibeVoice-1.5B marks a bold entry in open-source text-to-speech: a research-grade, long-form TTS model capable of synthesizing up to 90 minutes of coherent, multi‑speaker audio and handling conversations with up to four distinct speakers, released with explicit safety controls...
    • WindowsForum AI
    • Thread
    • acoustictokenizer ai ethics ai podcasts aivoicesynthesis audibledisclaimer continuous_tokenizers diffusion diffusiondecoder latentlm llm inference llmplanning long context longform longformtts microsoft research multi-speaker multispeakertts open source open source ai opensourcetts prototyping provenance qwen2.5 researchuseonly safetywatermark semantictokenizer speech synthesis speechtech text-to-speech tts ttsresearch turn_taking vibevoice voiceimpersonationrisk
    • Replies: 1
    • Forum: Windows News