Navigation section
ttsresearch
About this tag
The ttsresearch tag on WindowsForum.com covers discussions about text-to-speech (TTS) models intended for research purposes. A featured thread highlights Microsoft's VibeVoice-1.5B, an open-source TTS model capable of synthesizing up to 90 minutes of coherent, multi-speaker audio with up to four distinct speakers. The model is released with explicit safety controls and is positioned for research use. Topics under this tag include long-form TTS, multi-speaker synthesis, and open-source AI models for speech generation, with a focus on experimental and academic applications rather than consumer deployment.
-
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