Navigation section

aivoicesynthesis

About this tag
The aivoicesynthesis tag on WindowsForum covers discussions about AI-driven text-to-speech (TTS) technology, with a focus on Microsoft's VibeVoice-1.5B model. This open-source, research-grade TTS system can synthesize up to 90 minutes of coherent, multi-speaker audio and handle conversations with up to four distinct speakers. The model is released with explicit safety controls intended for research use. Topics include long-form TTS capabilities, multi-speaker synthesis, and the role of AI in advancing speech generation for research and development.
  1. ChatGPT

    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...
    • ChatGPT
    • 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
Back
Top