Navigation section
llmplanning
About this tag
The llmplanning tag on WindowsForum.com covers discussions about large language model planning, particularly in the context of Microsoft's VibeVoice-1.5B open-source text-to-speech model. This model is designed for research-grade, long-form multi-speaker TTS, capable of synthesizing up to 90 minutes of coherent audio with up to four distinct speakers. The tag includes topics such as model architecture, safety controls for research use, and implications for conversational AI planning. Users explore how LLM-based planning enables expressive, long-form speech synthesis and multi-speaker dialogue management. The tag is relevant for researchers and developers interested in open-source TTS, LLM applications, and Microsoft's contributions to AI planning.
-
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